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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74289
    Prev
    Next
    INDEX
    Explanations

    star

    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
     виправивши
    -0.78
     Савезне
    -0.71
    KURZBESCHREIBUNG
    -0.64
     internetowa
    -0.63
    ніципа
    -0.60
     समीक्षक
    -0.59
     iprot
    -0.59
    Spoljašnje
    -0.59
     مرئيه
    -0.59
    XmlAccessType
    -0.59
    POSITIVE LOGITS
     G
    0.61
    ProgressHUD
    0.55
    G
    0.53
    TintMode
    0.47
     K
    0.44
     star
    0.43
    TagMode
    0.43
     Gibraltar
    0.42
     dwarf
    0.42
     Star
    0.41
    Activations Density 0.000%

    No Known Activations