© 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. 38738
    Prev
    Next
    INDEX
    Explanations

    Text snippets from mixed sources

    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
     shaved
    -1.05
     /\.(
    -0.59
     link
    -0.56
    tivazione
    -0.54
    umah
    -0.52
     
    -0.50
     per
    -0.49
     case
    -0.49
     Living
    -0.49
    CrossRef
    -0.48
    POSITIVE LOGITS
    InjectAttribute
    0.83
    RTDA
    0.75
    MigrationBuilder
    0.72
    脚注の使い方
    0.70
    +#+#
    0.70
     surla
    0.69
     AppColors
    0.69
     hâte
    0.69
    oredCriteria
    0.68
    twimg
    0.66
    Activations Density 1.681%

    No Known Activations