© 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. 0-CLT-HP
    7. 97750
    Prev
    Next
    INDEX
    Explanations

    urt

    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
    ADELPHIA
    -1.02
    urt
    -0.87
    cited
    -0.85
     kasarigan
    -0.60
    ReusableCell
    -0.59
    pertory
    -0.58
    chie
    -0.54
    SerializeField
    -0.50
    iping
    -0.50
    IntoConstraints
    -0.49
    POSITIVE LOGITS
    RenderAtEndOf
    0.61
    glDisable
    0.54
    peq
    0.53
    usepackage
    0.52
     sī
    0.52
    struzioni
    0.50
    //
    0.50
    rijfs
    0.49
    dientemente
    0.49
    esar
    0.49
    Activations Density 0.095%

    No Known Activations