© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42967
    Prev
    Next
    INDEX
    Explanations

    rules, regulations

    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
     rule
    -1.67
     Rule
    -1.67
     Rules
    -1.54
    Rule
    -1.52
     RULE
    -1.48
     rules
    -1.45
    rule
    -1.43
    Rules
    -1.39
    rules
    -1.37
     RULES
    -1.30
    POSITIVE LOGITS
    Personensuche
    0.67
    曖昧さ回避
    0.63
    RTLD
    0.63
    MLLoader
    0.57
    исленность
    0.56
    новниш
    0.54
    book
    0.51
    bank
    0.48
    burger
    0.48
     MenuView
    0.48
    Activations Density 0.146%

    No Known Activations