© 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

    length function call

    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
     abs
    -0.08
    qrt
    -0.06
     Calculate
    -0.05
    ab
    -0.04
    etween
    -0.04
     math
    -0.04
     elif
    -0.04
    ta
    -0.03
     del
    -0.03
    .append
    -0.02
    Positive Logits
     each
    0.07
    .strip
    0.04
    ique
    0.04
    lat
    0.03
    itude
    0.03
     lat
    0.03
     whe
    0.02
    ge
    0.02
     all
    0.02
    put
    0.02
    Activations Density 91.621%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list element access (negative activations)

    python-code · gemini-2.5-flash-lite

    tuple index access

    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
    rack
    -0.04
    .e
    -0.03
     /
    -0.02
    .c
    -0.02
     If
    -0.02
    .random
    -0.01
     form
    -0.01
    bab
    -0.01
    .append
    -0.01
     -=
    -0.01
    Positive Logits
     found
    0.03
     while
    0.03
    ow
    0.03
     iter
    0.02
    fset
    0.02
    over
    0.02
     possible
    0.01
    hor
    0.01
     directions
    0.01
    .index
    0.01
    Activations Density 98.204%

    No Known Activations