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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16341
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sports teams, scores, and game outcomes

    oai_token-act-pair · gemini-2.0-flash

    [no clear pattern]

    np_token-act-pair-logits · gemini-2.0-flash

    Sports teams/matches

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     nahilalakip
    -0.59
     enemy
    -0.58
    敵
    -0.56
     veneta
    -0.54
     rivalry
    -0.54
    RegressionTest
    -0.52
     adversary
    -0.51
     rivales
    -0.51
    加坡
    -0.51
     devriez
    -0.51
    POSITIVE LOGITS
    basicConfig
    0.80
     BorderRadius
    0.64
    extAlignment
    0.63
    migrationBuilder
    0.63
     RoutedEventArgs
    0.60
    createStatement
    0.57
    initComponents
    0.57
    ChildScrollView
    0.56
    ContentAsync
    0.54
     TimeUnit
    0.54
    Activations Density 1.565%

    No Known Activations