© 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. 4-CLT-HP
    7. 4432
    Prev
    Next
    INDEX
    Explanations

    you

    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
     <>",
    -0.56
    stasia
    -0.53
    loves
    -0.52
    exists
    -0.51
    atrix
    -0.50
     popularity
    -0.50
    mely
    -0.50
    ThemeOverlay
    -0.49
     exemplifies
    -0.48
    방
    -0.48
    POSITIVE LOGITS
     can
    0.69
    fjspx
    0.63
    ArrowToggle
    0.61
     بيها
    0.59
     never
    0.57
    <bos>
    0.55
     then
    0.55
    complexType
    0.52
    capai
    0.51
     nahilalakip
    0.51
    Activations Density 0.002%

    No Known Activations