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. 0-CLT-HP
    4. 40835
    Prev
    Next
    INDEX
    Explanations

    constrained

    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
    <bos>
    -1.78
    '
    -0.49
     Paglinawan
    -0.49
    Personensuche
    -0.47
     történ
    -0.42
    HideFlags
    -0.42
    ↵↵
    -0.41
     astfel
    -0.41
    ↵
    -0.40
    FormTagHelper
    -0.37
    POSITIVE LOGITS
    __*/
    0.79
    gaged
    0.71
    parsedMessage
    0.69
    mone
    0.68
    }`;
    0.68
     istr
    0.66
    ArgsConstructor
    0.66
     متعلقه
    0.64
    itarian
    0.64
    ÉM
    0.64
    Activations Density 0.031%

    No Known Activations