© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    call to len() function (negative activations)

    python-code · gemini-2.5-flash-lite

    if statement condition

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     return
    -0.04
     Returns
    -0.04
     Return
    -0.04
    turn
    -0.03
     raise
    -0.02
    urn
    -0.02
     :
    -0.01
     sele
    -0.01
     given
    -0.01
     Output
    -0.01
    Positive Logits
    uel
    0.02
    _cost
    0.01
    value
    0.01
     lat
    0.01
     cost
    0.01
    rice
    0.01
    riority
    0.01
     val
    0.01
     values
    0.01
     &
    0.01
    Activations Density 92.655%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    parentheses and brackets in calls (negative activations)

    python-code · gemini-2.5-flash-lite

    math module functions

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    input
    -0.06
     input
    -0.05
    _input
    -0.05
    (input
    -0.04
    .txt
    -0.04
    ample
    -0.04
    structions
    -0.03
    En
    -0.03
    _with
    -0.03
    ith
    -0.03
    Positive Logits
    uples
    0.05
    uple
    0.05
     abs
    0.03
    .write
    0.03
    ab
    0.03
    qrt
    0.03
    mbol
    0.02
     tuple
    0.02
    ameters
    0.02
    lit
    0.02
    Activations Density 91.641%

    No Known Activations