© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13283
    Prev
    Next
    INDEX
    Explanations

    instances where code imports multiple modules

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     export
    -1.27
    sizeCache
    -1.20
     Export
    -1.19
     exported
    -1.16
     EXPORT
    -1.13
    __":
    -1.12
     ModelExpression
    -1.10
    WriteBarrier
    -1.10
    UserScript
    -1.09
     import
    -1.09
    POSITIVE LOGITS
    .
    0.68
    import
    0.65
    oarece
    0.55
     immagin
    0.46
     quam
    0.44
     venons
    0.43
    cuerdo
    0.42
    ;
    0.41
    ,
    0.40
    گار
    0.39
    Activations Density 0.010%

    No Known Activations