© 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. 0-CLT-HP
    4. 38982
    Prev
    Next
    INDEX
    Explanations

    achievements

    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
    ar
    -0.65
    ly
    -0.63
     achievements
    -0.63
    rrh
    -0.62
    i
    -0.59
     achievement
    -0.59
    id
    -0.54
    WARD
    -0.54
     Efficient
    -0.52
    achievement
    -0.52
    POSITIVE LOGITS
     متعلقه
    0.75
    GEBURTSDATUM
    0.68
    yntaxException
    0.68
    HtmlAttribute
    0.65
     cherchés
    0.64
     فريبيس
    0.63
    IsMutable
    0.63
     rhestr
    0.62
     виправивши
    0.61
    intios
    0.61
    Activations Density 0.220%

    No Known Activations