© 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. 12290
    Prev
    Next
    INDEX
    Explanations

    I/Quotation Marks

    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
     amitié
    -0.78
    <em>
    -0.75
     enfans
    -0.75
     dieux
    -0.73
     pauv
    -0.73
     vérit
    -0.71
    CppMethod
    -0.69
     volontaire
    -0.69
     coû
    -0.68
     épais
    -0.68
    POSITIVE LOGITS
    :✨
    0.67
     EconPapers
    0.65
     дописавши
    0.63
    
    0.61
    fieldId
    0.49
     pinulongan
    0.47
     
    0.46
     GB
    0.45
     kasarigan
    0.45
     lul
    0.45
    Activations Density 0.204%

    No Known Activations