Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4210
    Prev
    Next
    INDEX
    Explanations

    Parentheses/Braces

    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
    хьтан
    -0.65
    elemField
    -0.60
     propOrder
    -0.57
    InjectAttribute
    -0.54
    istoitu
    -0.52
    plotlib
    -0.52
    νομα
    -0.50
    jsxFileName
    -0.50
     Signalez
    -0.48
    lüssel
    -0.47
    POSITIVE LOGITS
     essentiellement
    0.57
    postcss
    0.56
    ScopeManager
    0.56
    صدر
    0.55
    主要是
    0.52
    mostly
    0.51
    PhysRev
    0.50
     piemē
    0.50
     mostly
    0.50
     Inscrivez
    0.49
    Activations Density 0.001%

    No Known Activations