© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3316
    Prev
    Next
    INDEX
    Explanations

    numbers or identifiers

    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
     tartalomajánló
    -0.65
    tagHelperRunner
    -0.60
    makeConstraints
    -0.56
    IntoConstraints
    -0.56
    AccessorTable
    -0.54
     jugu
    -0.53
     kiện
    -0.52
    oughly
    -0.52
     vanta
    -0.50
    permitAll
    -0.50
    POSITIVE LOGITS
     cię
    0.52
    RTEX
    0.50
    Obrázky
    0.50
    icoot
    0.50
    حياته
    0.50
     Gerv
    0.49
    GeneratedCode
    0.48
    Билгалдахарш
    0.48
    StackNavigator
    0.48
    DeleteBehavior
    0.48
    Activations Density 0.002%

    No Known Activations