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. 22-CLT-HP
    4. 74347
    Prev
    Next
    INDEX
    Explanations

    BSD

    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
     للاسماء
    -1.27
    StoryboardSegue
    -0.96
    LookAnd
    -0.83
    setVerticalGroup
    -0.73
    ыгана
    -0.70
    reactstrap
    -0.70
    Portail
    -0.65
    原始内容存档于
    -0.64
     AssemblyProduct
    -0.64
     ویکی‌پدی
    -0.62
    POSITIVE LOGITS
    Full
    0.52
    OrBuilder
    0.47
     Full
    0.46
     buch
    0.41
    Buch
    0.40
    libft
    0.39
    +#+
    0.39
    full
    0.39
    getFull
    0.39
     ſtate
    0.39
    Activations Density 0.002%

    No Known Activations