© 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. 1-CLT-HP
    7. 279
    Prev
    Next
    INDEX
    Explanations

    weds

    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
    arthed
    -0.54
    dì
    -0.51
    ionage
    -0.51
    chafter
    -0.50
    tableFuture
    -0.50
    Tracce
    -0.49
    vations
    -0.48
     daya
    -0.47
    XtraReports
    -0.46
     cima
    -0.45
    POSITIVE LOGITS
    IsMutable
    0.69
    EDEFAULT
    0.68
    يميديا
    0.58
    CodedInputStream
    0.57
    initializeApp
    0.56
    にほんブログ村
    0.55
     BorderRadius
    0.54
     تضيفلها
    0.54
    FXML
    0.52
     larmes
    0.52
    Activations Density 0.023%

    No Known Activations