© 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. 97596
    Prev
    Next
    INDEX
    Explanations

    official publications/documents

    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
     myſelf
    -0.69
     Monfieur
    -0.65
     avoient
    -0.63
     Efq
    -0.58
     Theſe
    -0.57
    seamnă
    -0.56
     uſed
    -0.55
     étoit
    -0.55
    μεν
    -0.55
     itſelf
    -0.55
    POSITIVE LOGITS
    HtmlAttribute
    0.85
    UnusedPrivate
    0.82
     typelib
    0.74
     Infórmanos
    0.69
     defaultstate
    0.69
     @"/
    0.68
    تقاوى
    0.67
    colgroup
    0.65
    abestanden
    0.65
    XmlAccessType
    0.63
    Activations Density 0.080%

    No Known Activations