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. 12798
    Prev
    Next
    INDEX
    Explanations

    Orders, rules, commands

    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
     تانيه
    -0.75
     StringTokenizer
    -0.59
    RenderAtEndOf
    -0.56
     satunya
    -0.50
     thereto
    -0.50
     served
    -0.50
    terdam
    -0.50
     thereof
    -0.49
    ":[{
    -0.48
     ơn
    -0.47
    POSITIVE LOGITS
     referenties
    0.60
    Portály
    0.60
    quins
    0.57
    ViewFeatures
    0.54
    Aiheesta
    0.54
    ondissement
    0.54
     Purg
    0.52
     Roskov
    0.52
    vatar
    0.51
    CONCURRENT
    0.51
    Activations Density 0.015%

    No Known Activations