© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4360
    Prev
    Next
    INDEX
    Explanations

    biographies

    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
    oredCriteria
    -0.68
     consultato
    -0.66
    ArgsConstructor
    -0.65
    ThroughAttribute
    -0.65
    abetes
    -0.63
    givers
    -0.62
    MigrationBuilder
    -0.61
     Roskov
    -0.61
    bearers
    -0.60
     lenker
    -0.60
    POSITIVE LOGITS
     player
    0.61
     athlete
    0.58
     officer
    0.54
     person
    0.54
     man
    0.53
     youngster
    0.53
     worker
    0.50
     operator
    0.49
     fighter
    0.49
    sodik
    0.48
    Activations Density 0.037%

    No Known Activations