© 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. 0-CLT-HP
    7. 91913
    Prev
    Next
    INDEX
    Explanations

    Adding

    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
     négociations
    -0.64
     AssemblyCulture
    -0.61
     réunions
    -0.58
     attentes
    -0.57
     spectateurs
    -0.56
    Add
    -0.56
     médicaux
    -0.55
     edelstahl
    -0.54
     météo
    -0.54
     originaux
    -0.54
    POSITIVE LOGITS
    migrationBuilder
    0.70
    UnitTesting
    0.67
    WaitGroup
    0.67
    IsContent
    0.64
    VersionUID
    0.60
    protoimpl
    0.57
    zzleHttp
    0.57
    scape
    0.54
    abinieri
    0.54
    )['
    0.54
    Activations Density 0.167%

    No Known Activations