© 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. 45206
    Prev
    Next
    INDEX
    Explanations

    anatomical contexts

    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
     resumes
    -0.87
    su
    -0.75
    Su
    -0.71
     Su
    -0.64
     مشين
    -0.61
     su
    -0.60
    tn
    -0.59
     reigns
    -0.57
     excuse
    -0.57
    MigrationBuilder
    -0.57
    POSITIVE LOGITS
     Paglinawan
    0.66
     ModelExpression
    0.65
    SequentialGroup
    0.58
     Arbeiter
    0.57
     DbType
    0.55
     للاسماء
    0.55
    Tembelea
    0.53
    migrationBuilder
    0.52
    SBATCH
    0.52
    NameInMap
    0.50
    Activations Density 0.119%

    No Known Activations