© 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. 1162
    Prev
    Next
    INDEX
    Explanations

    just

    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
     just
    -1.80
    just
    -1.54
     Just
    -1.38
    Just
    -1.36
     juste
    -1.05
     JUST
    -0.98
    JUST
    -0.91
     justo
    -0.72
     appena
    -0.66
     can
    -0.64
    POSITIVE LOGITS
    expandindo
    0.95
    MigrationBuilder
    0.85
     dandy
    0.78
    RenderAtEndOf
    0.75
     فريبيس
    0.75
     GIPHY
    0.73
    ngdoc
    0.66
     transitory
    0.65
     Adieu
    0.65
     Мексичка
    0.64
    Activations Density 0.113%

    No Known Activations