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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97963
    Prev
    Next
    INDEX
    Explanations

    battle

    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
     Battle
    -0.81
     battle
    -0.80
    MING
    -0.61
    Battle
    -0.61
    ming
    -0.57
     roller
    -0.53
    NESDAY
    -0.53
     BATTLE
    -0.50
     Roller
    -0.48
     roll
    -0.47
    POSITIVE LOGITS
    findpost
    0.75
    providedIn
    0.70
    IntoConstraints
    0.67
     resourceCulture
    0.66
     للمعارف
    0.62
    참고
    0.60
    UnsafeEnabled
    0.60
    stylers
    0.60
    game
    0.59
    hoeddwyd
    0.59
    Activations Density 0.097%

    No Known Activations