© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45215
    Prev
    Next
    INDEX
    Explanations

    player

    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
     player
    -2.03
    player
    -1.46
     Player
    -1.45
    Player
    -1.33
     participant
    -1.21
     PLAYER
    -1.15
    PLAYER
    -1.04
     players
    -1.02
     candidate
    -1.00
     jugador
    -0.97
    POSITIVE LOGITS
     itſelf
    0.71
     malheure
    0.70
     hâte
    0.70
     betale
    0.68
     présidenti
    0.67
     SwitchCompat
    0.66
     Efq
    0.66
     exécut
    0.66
     tarko
    0.66
     Lipschitz
    0.66
    Activations Density 0.112%

    No Known Activations