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. 74384
    Prev
    Next
    INDEX
    Explanations

    topics from research articles

    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
    はじめに
    -0.68
    +#+#
    -0.64
    :✨
    -0.58
    BorderFactory
    -0.57
    DeleteBehavior
    -0.57
    ,:);
    -0.57
    sizeCache
    -0.56
    libft
    -0.55
     mergeFrom
    -0.53
     MonoBehaviour
    -0.53
    POSITIVE LOGITS
    data
    0.48
    ulkan
    0.46
    ple
    0.46
     "#"
    0.44
    beat
    0.44
     data
    0.43
    pacs
    0.43
    heet
    0.41
    Зноскі
    0.41
     "'";
    0.40
    Activations Density 0.005%

    No Known Activations