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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14165
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sports tournaments and results

    oai_token-act-pair · gemini-2.0-flash

    game

    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
     ControllerBase
    -0.61
    DispatchToProps
    -0.60
     nakalista
    -0.60
     prête
    -0.53
     interviewer
    -0.53
     pageContext
    -0.52
    rokken
    -0.52
    phinx
    -0.52
     canlynol
    -0.51
    pilot
    -0.50
    POSITIVE LOGITS
     game
    0.92
    game
    0.73
     Game
    0.67
    WEBPACK
    0.63
    Game
    0.63
     partita
    0.60
     games
    0.57
    ゲーム
    0.55
     GAME
    0.54
    GEBURTSDATUM
    0.54
    Activations Density 0.802%

    No Known Activations