© 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. 1-CLT-HP
    7. 45747
    Prev
    Next
    INDEX
    Explanations

    social

    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
     Social
    -0.66
    Social
    -0.65
    interopRequire
    -0.63
     social
    -0.63
    social
    -0.58
     kaarangay
    -0.57
     SOCIAL
    -0.55
     OFDb
    -0.55
     sociales
    -0.55
     ImportError
    -0.52
    POSITIVE LOGITS
     betweenstory
    0.64
    KommentareTeilen
    0.55
    SharedCtor
    0.52
    ConstraintMaker
    0.52
    出版年
    0.52
    ites
    0.51
    ity
    0.51
    istically
    0.50
    ite
    0.50
     ModelExpression
    0.50
    Activations Density 0.008%

    No Known Activations