© 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. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6823
    Prev
    Next
    INDEX
    Explanations

    sequences of numeric and symbolic tokens, often resembling structured data or code

    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
    omonas
    -0.55
    endon
    -0.55
     aDecoder
    -0.54
    ((((
    -0.54
    ">${
    -0.49
     Ayu
    -0.48
    anskje
    -0.47
    rylic
    -0.46
    zm
    -0.46
    ROLLER
    -0.46
    POSITIVE LOGITS
     يتيمه
    0.96
     ModelExpression
    0.72
    kloped
    0.71
     ویکی‌پدیا
    0.69
     ExecuteAsync
    0.69
    IndentedString
    0.69
    ViewFeatures
    0.68
     متعلقه
    0.65
     onOptions
    0.65
    providedIn
    0.64
    Activations Density 0.066%

    No Known Activations