© 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. 1230
    Prev
    Next
    INDEX
    Explanations

    over

    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
    InjectAttribute
    -0.67
    Enllaces
    -0.56
    Dữ
    -0.51
    Diwedd
    -0.51
    featureID
    -0.51
    Notae
    -0.49
    dafx
    -0.48
    脚注の使い方
    -0.47
     Examiner
    -0.47
     Bạn
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.60
     typelib
    0.56
    HasAnnotation
    0.56
    MigrationBuilder
    0.54
     disambiguazione
    0.53
     lays
    0.51
     المعيارى
    0.50
     surla
    0.49
     Walkover
    0.49
    reportWebVitals
    0.48
    Activations Density 0.003%

    No Known Activations