© 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. 96082
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Audiodateien
    -0.58
    مراجع
    -0.54
    migrationBuilder
    -0.52
    Lähteet
    -0.49
    httphttps
    -0.48
    Legături
    -0.47
    ══
    -0.45
    יקר
    -0.45
    Blurb
    -0.45
    المراجع
    -0.43
    POSITIVE LOGITS
     surla
    0.63
    RegressionTest
    0.58
    AddTagHelper
    0.58
     defeating
    0.58
    فاض
    0.57
     improving
    0.57
     ویکی‌پدیای
    0.56
     preparing
    0.56
     notifying
    0.56
     celebrating
    0.54
    Activations Density 0.002%

    No Known Activations