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. 40883
    Prev
    Next
    INDEX
    Explanations

    brethren

    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
     itſelf
    -1.00
    StoryboardSegue
    -0.99
     تانيه
    -0.94
    ſelves
    -0.92
    ^(@)
    -0.88
    etheless
    -0.88
    InputBorder
    -0.88
    theless
    -0.87
     NSCoder
    -0.87
     Efq
    -0.85
    POSITIVE LOGITS
    ’
    0.67
    .
    0.65
    ,
    0.64
     who
    0.60
    y
    0.59
    '
    0.58
     of
    0.57
     in
    0.57
     (
    0.54
    -
    0.53
    Activations Density 0.132%

    No Known Activations