© 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. 5-CLT-HP
    7. 2217
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs

    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
    kegaard
    -0.59
    thom
    -0.50
    Bara
    -0.50
    JC
    -0.48
    ég
    -0.48
    Sera
    -0.47
    CFS
    -0.47
    MessageOf
    -0.47
    Bunch
    -0.47
     AssemblyCulture
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    0.75
     "..\..\
    0.70
    WebServlet
    0.63
     IBOutlet
    0.60
     "..\..\..\
    0.56
    InjectAttribute
    0.55
    رشف
    0.55
    Цель
    0.54
    новниш
    0.54
    новништво
    0.54
    Activations Density 0.005%

    No Known Activations