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. 40849
    Prev
    Next
    INDEX
    Explanations

    anti

    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
     anti
    -0.77
     Anti
    -0.63
    ↵
    -0.60
     "
    -0.59
     
    -0.58
    ↵↵
    -0.57
    <eos>
    -0.56
     c
    -0.55
     des
    -0.55
    Anti
    -0.55
    POSITIVE LOGITS
     оригіналу
    1.09
    ſelf
    1.05
     تضيفلها
    1.04
     itſelf
    1.02
    RectangleBorder
    1.01
     ―――――
    1.01
    mybatisplus
    0.99
     bezeichneter
    0.97
     auffi
    0.96
     Monfieur
    0.96
    Activations Density 0.186%

    No Known Activations