© 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
    No Explanations Found
    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
    (op
    -0.10
     operation
    -0.08
    :↵
    -0.07
     >=
    -0.06
    ob
    -0.06
     <=
    -0.06
    [-
    -0.05
    ',↵
    -0.05
     !=
    -0.05
    }")↵↵
    -0.05
    Positive Logits
     visited
    0.05
    07
    0.04
    01
    0.04
    03
    0.04
    00
    0.03
    02
    0.03
    0
    0.03
    05
    0.03
    000
    0.03
    08
    0.03
    Activations Density 7.327%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function arguments or variable assignments

    python-code · gemini-2.5-flash-lite

    member of a class definition (negative activations)

    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
    ot
    -0.04
    own
    -0.04
     ny
    -0.03
    ow
    -0.03
    uples
    -0.02
    xp
    -0.02
    der
    -0.02
    ls
    -0.02
    ordinate
    -0.02
    ati
    -0.02
    Positive Logits
     ac
    0.05
    ames
    0.04
    ac
    0.04
    ic
    0.04
     name
    0.04
    ateg
    0.04
    name
    0.03
    90
    0.03
     other
    0.03
     **
    0.03
    Activations Density 100.000%

    No Known Activations