© 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. 5-CLT-HP
    7. 2087
    Prev
    Next
    INDEX
    Explanations

    import

    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
    ReusableCell
    -0.69
    ῖς
    -0.57
     himo
    -0.56
     محفوظة
    -0.50
     cuantas
    -0.49
     Vrbo
    -0.48
    cinogenicity
    -0.48
    UnsafeEnabled
    -0.48
    ylase
    -0.48
     للمعارف
    -0.47
    POSITIVE LOGITS
     of
    0.63
     Bug
    0.60
    Bug
    0.56
     mukana
    0.52
    bug
    0.51
    HtmlAttribute
    0.51
    ziek
    0.50
     displacement
    0.49
    bumptech
    0.49
     Found
    0.48
    Activations Density 0.003%

    No Known Activations