© 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. 5-CLT-HP
    4. 1235
    Prev
    Next
    INDEX
    Explanations

    in

    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
    SharedCtor
    -0.80
    setVerticalGroup
    -0.77
    tvguidetime
    -0.73
     ModelExpression
    -0.72
     Taktlose
    -0.71
    RegressionTest
    -0.71
     noDo
    -0.69
    IUrlHelper
    -0.69
     kaarangay
    -0.69
    RetentionPolicy
    -0.68
    POSITIVE LOGITS
    ائح
    0.41
     feelings
    0.41
     الوطنيه
    0.38
    WebElementEntity
    0.38
     such
    0.37
    øya
    0.36
     Hawaii
    0.36
     as
    0.36
     hoạch
    0.35
     ogr
    0.34
    Activations Density 0.001%

    No Known Activations