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. 2129
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and contractions

    oai_token-act-pair · gemini-2.0-flash

    I

    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
    __*/
    -0.67
     JADX
    -0.64
    CodeAttribute
    -0.62
     autorytatywna
    -0.59
    queryInterface
    -0.59
    MIDDLEWARE
    -0.58
     nahilalakip
    -0.57
    ContentAlignment
    -0.57
    ftagPool
    -0.56
    BagLayout
    -0.56
    POSITIVE LOGITS
     fuga
    0.55
     åt
    0.52
    createTextNode
    0.52
     ویکی‌پدیای
    0.51
     Fle
    0.50
    TIMORE
    0.50
    一看
    0.48
     MenuView
    0.48
     we
    0.47
     spiller
    0.47
    Activations Density 0.355%

    No Known Activations