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. 1-CLT-HP
    4. 11288
    Prev
    Next
    INDEX
    Explanations

    names

    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
     Sewell
    -0.47
     Lutz
    -0.46
    berra
    -0.46
    Хро
    -0.45
    parte
    -0.45
     Otero
    -0.45
     marshal
    -0.44
    ombic
    -0.43
    irus
    -0.43
     PGC
    -0.42
    POSITIVE LOGITS
    DockStyle
    1.02
     متعلقه
    0.90
    ItemBackground
    0.85
     AssemblyCulture
    0.81
     صوتيه
    0.81
     @"/
    0.71
     فريبيس
    0.69
    ContentAsync
    0.67
    RectangleBorder
    0.66
    OGND
    0.65
    Activations Density 0.016%

    No Known Activations