© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 3
    Prev
    Next
    INDEX
    Explanations

    import statement or attribute access

    python-code · gemini-2.5-flash-lite

    collections.defaultdict (negative activations)

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    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
    Not in Any Lists

    No Comments

    Negative Logits
    lambda
    -0.29
    ome
    -0.28
    me
    -0.23
    ļ
    -0.22
    om
    -0.19
    oly
    -0.16
    oc
    -0.15
    _co
    -0.13
    58
    -0.09
    â
    -0.08
    POSITIVE LOGITS
    _capacity
    0.14
    class
    0.13
    lass
    0.12
    _order
    0.11
    j
    0.11
    **
    0.11
    _coords
    0.10
    _col
    0.09
    col
    0.09
     order
    0.08
    Activations Density 100.000%

    No Known Activations