© 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. 0-RES-MATRYOSHKA-DC
    7. 12271
    Prev
    Next
    INDEX
    Explanations

    expressions related to the importance of a specific part within a larger whole

    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
    LookAnd
    -1.03
    abestanden
    -0.98
     Мексичка
    -0.92
    InjectAttribute
    -0.88
    MigrationBuilder
    -0.86
     समीक्षाओं
    -0.84
     ویکی‌پدیا
    -0.83
     المعيارى
    -0.82
    IUrlHelper
    -0.82
    addCriterion
    -0.81
    POSITIVE LOGITS
     existence
    0.45
    a
    0.44
    bs
    0.44
    cita
    0.43
     attention
    0.43
     assolutamente
    0.42
    ing
    0.42
    able
    0.42
    ann
    0.42
    la
    0.42
    Activations Density 0.090%

    No Known Activations