© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93127
    Prev
    Next
    INDEX
    Explanations

    game

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     game
    -1.65
    game
    -1.13
     GAME
    -1.01
     Game
    -1.00
    Game
    -0.99
     gioco
    -0.94
     jogo
    -0.92
     juego
    -0.91
    ConstraintMaker
    -0.90
     permainan
    -0.88
    POSITIVE LOGITS
    RegressionTest
    0.50
     Faul
    0.49
     catered
    0.48
     GENTLE
    0.48
     كورة
    0.46
     bor
    0.45
     inherits
    0.44
    Dislikes
    0.44
    GENT
    0.42
     audits
    0.41
    Activations Density 0.057%

    No Known Activations