© 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. 1-CLT-HP
    7. 13183
    Prev
    Next
    INDEX
    Explanations

    power

    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
     Italijanski
    -0.55
    Diwedd
    -0.52
     demonstration
    -0.50
    gestone
    -0.50
     nodule
    -0.50
     fus
    -0.49
    COURS
    -0.49
     lento
    -0.49
    Zip
    -0.48
    turo
    -0.48
    POSITIVE LOGITS
    IntoConstraints
    0.65
    modelBuilder
    0.63
     تانيه
    0.60
    <?>>
    0.60
     Meksiku
    0.60
    HasForeignKey
    0.60
     ioutil
    0.59
    DockStyle
    0.59
    GraphicsUnit
    0.58
    AnimationsModule
    0.54
    Activations Density 0.045%

    No Known Activations