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. 40799
    Prev
    Next
    INDEX
    Explanations

    object

    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
     purpoſe
    -1.02
     object
    -0.98
    ſelves
    -0.97
     myſelf
    -0.96
     pleaſure
    -0.95
     itſelf
    -0.94
    ſelf
    -0.92
     objects
    -0.91
    object
    -0.84
     Reſ
    -0.83
    POSITIVE LOGITS
    (
    0.57
     of
    0.55
    ’
    0.55
     for
    0.54
    '
    0.50
     in
    0.48
     Bor
    0.46
     (
    0.46
    ‘
    0.46
     C
    0.46
    Activations Density 0.651%

    No Known Activations