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. 11047
    Prev
    Next
    INDEX
    Explanations

    size

    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
     通販
    -0.66
    EDEFAULT
    -0.66
    الحياه
    -0.65
    kheim
    -0.63
    mercado
    -0.63
     وتسجيلات
    -0.63
    shadowOffset
    -0.62
    HasColumnName
    -0.61
    dafx
    -0.60
    PHeader
    -0.59
    POSITIVE LOGITS
    )))),
    0.42
    */
    0.41
    "./
    0.39
    )))));
    0.39
    Weblinks
    0.38
    })]
    0.38
     zij
    0.37
     Luk
    0.37
    Explanation
    0.36
    らし
    0.36
    Activations Density 0.011%

    No Known Activations