Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16332
    Prev
    Next
    INDEX
    Explanations

    mentions of figures and supplementary materials in research papers

    oai_token-act-pair · gemini-2.0-flash

    Figures, tables, supplementary material

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    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
     kasarigan
    -0.97
    TypedDataSet
    -0.79
    ⓧ
    -0.78
    jspb
    -0.77
     оригіналу
    -0.73
     '\\;'
    -0.73
     ویکی‌پدیای
    -0.72
    évaluateur
    -0.71
    rungsseite
    -0.71
    LookAnd
    -0.71
    POSITIVE LOGITS
     ziehen
    0.44
    ondy
    0.42
     säkert
    0.42
    ysm
    0.41
    Me
    0.40
    ouse
    0.39
    pseud
    0.39
    acons
    0.39
     legen
    0.38
     striped
    0.38
    Activations Density 2.187%

    No Known Activations