© 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

    function call arguments or parameters

    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
    form
    -0.03
    ame
    -0.02
    ake
    -0.02
    isit
    -0.01
     p
    -0.01
    hor
    -0.01
     each
    -0.01
    ."""↵
    -0.01
    ain
    -0.01
    "{
    -0.01
    Positive Logits
     M
    0.05
     N
    0.04
    Ö
    0.04
     Testing
    0.03
    N
    0.03
     Def
    0.03
     Calculate
    0.03
     Initialize
    0.03
    .m
    0.03
     Define
    0.03
    Activations Density 10.951%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    class definitions and methods

    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
    \
    -0.02
     continue
    -0.02
    ^
    -0.02
    [neighbor
    -0.02
    ?
    -0.02
    ays
    -0.02
    ute
    -0.02
    .de
    -0.02
    ad
    -0.02
    neighbor
    -0.02
    Positive Logits
    ()
    0.05
    ol
    0.05
     Create
    0.05
    itial
    0.04
    visited
    0.04
    stance
    0.03
     visited
    0.03
     Initialize
    0.03
    ")
    0.03
    class
    0.03
    Activations Density 74.090%

    No Known Activations