Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74107
    Prev
    Next
    INDEX
    Explanations

    technical language

    np_max-act-logits · 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
     EnglishChoose
    -0.58
     AttributeSet
    -0.54
     NSCoder
    -0.54
     revanche
    -0.52
    
    -0.50
     Tratado
    -0.49
     saites
    -0.49
    hæng
    -0.48
     szóci
    -0.47
     pā
    -0.47
    POSITIVE LOGITS
     Waray
    0.66
    цездатний
    0.64
    ViewImports
    0.60
    HtmlAttribute
    0.53
     Basi
    0.50
     nahilalakip
    0.49
     JADX
    0.49
    titleMargin
    0.49
    uxxxx
    0.49
    oulli
    0.48
    Activations Density 0.002%

    No Known Activations