© 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. 5-CLT-HP
    7. 96035
    Prev
    Next
    INDEX
    Explanations

    I

    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
     am
    -0.74
     nahilalakip
    -0.73
     myself
    -0.61
     nakalista
    -0.61
     EconPapers
    -0.60
     was
    -0.57
    am
    -0.55
    AMIENTO
    -0.54
    ím
    -0.53
     vitt
    -0.52
    POSITIVE LOGITS
    клопе
    0.63
    ImageContext
    0.54
    nocache
    0.52
     '{@
    0.52
     defaultstate
    0.52
    dba
    0.51
    oredCriteria
    0.51
     autorytatywna
    0.51
     that
    0.50
    MigrationBuilder
    0.50
    Activations Density 0.002%

    No Known Activations