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. 40808
    Prev
    Next
    INDEX
    Explanations

    accredited

    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
     independent
    -0.77
     Independent
    -0.57
     INDEPENDENT
    -0.57
     Wood
    -0.57
    WithIOException
    -0.55
     ID
    -0.51
     unabhäng
    -0.50
     V
    -0.48
     accredited
    -0.48
    independent
    -0.48
    POSITIVE LOGITS
     Majefty
    1.03
     myſelf
    1.02
     pleaſure
    1.00
     Monfieur
    1.00
     ſeveral
    1.00
     ſmall
    0.98
     fevere
    0.96
     Reſ
    0.96
     Diſ
    0.95
     itſelf
    0.95
    Activations Density 0.087%

    No Known Activations