© 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
    |>
    -0.13
    ].
    -0.12
    lit
    -0.10
     as
    -0.07
    _dep
    -0.06
    ut
    -0.05
                                    
    -0.05
    '.
    -0.04
    _distances
    -0.04
    _city
    -0.04
    Positive Logits
     or
    0.06
    (self
    0.05
     self
    0.04
    self
    0.04
    č
    0.04
    (node
    0.03
    [node
    0.03
     Node
    0.03
     node
    0.03
    Node
    0.03
    Activations Density 70.929%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    adding or deleting node

    python-code · gemini-2.5-flash-lite

    list item or number (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
    ative
    -0.09
    ion
    -0.08
     Calculate
    -0.08
    ber
    -0.08
    ance
    -0.07
    ied
    -0.07
    ren
    -0.07
    ations
    -0.06
    utes
    -0.06
    istic
    -0.06
    Positive Logits
     graph
    0.08
    graph
    0.08
    _graph
    0.08
    raph
    0.08
    .graph
    0.08
    network
    0.07
    etwork
    0.07
    ree
    0.07
    (graph
    0.07
     Graph
    0.06
    Activations Density 100.000%

    No Known Activations