© 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. 40028
    Prev
    Next
    INDEX
    Explanations

    lead

    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
    تقاوى
    -0.88
     فريبيس
    -0.71
    tvguidetime
    -0.69
     betweenstory
    -0.64
     enfans
    -0.59
    více
    -0.58
    Enllaços
    -0.57
    setVerticalGroup
    -0.57
    ℗
    -0.57
    êmios
    -0.56
    POSITIVE LOGITS
     to
    0.60
     retinal
    0.56
     clinically
    0.54
     renal
    0.54
     lymp
    0.53
    ServletException
    0.52
     bone
    0.51
    migrationBuilder
    0.51
     glaucoma
    0.50
     dilated
    0.50
    Activations Density 0.217%

    No Known Activations