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. 12936
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     виправивши
    -0.85
     متعلقه
    -0.83
     وتسجيلات
    -0.77
    +#+#
    -0.77
     ProtoMessage
    -0.76
     unknownFields
    -0.74
     صوتيه
    -0.72
     Normdatei
    -0.72
    aarrggbb
    -0.71
    yntaxException
    -0.70
    POSITIVE LOGITS
     
    0.60
     of
    0.50
     T
    0.46
     t
    0.44
     "
    0.43
     for
    0.42
    ↵
    0.42
     at
    0.41
     “
    0.40
     V
    0.40
    Activations Density 0.009%

    No Known Activations