© 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. 3447
    Prev
    Next
    INDEX
    Explanations

    ary

    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
     InputDecoration
    -0.47
    czaj
    -0.45
    Laz
    -0.44
     noqa
    -0.44
    HandlerContext
    -0.44
     tocando
    -0.43
    formazioni
    -0.43
    lagte
    -0.43
     setId
    -0.41
     guapo
    -0.41
    POSITIVE LOGITS
     propOrder
    0.69
     capital
    0.65
    expandindo
    0.63
     sums
    0.61
     تضيفلها
    0.61
     TAMBÉM
    0.60
    CascadeType
    0.57
    MigrationBuilder
    0.56
     credit
    0.56
     rate
    0.56
    Activations Density 0.002%

    No Known Activations