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. 22-CLT-HP
    4. 74342
    Prev
    Next
    INDEX
    Explanations

    webpack

    np_max-act-logits · 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
     CreateTagHelper
    -0.72
    ForValue
    -0.64
     hitting
    -0.63
    encodeWith
    -0.63
    OrBuilder
    -0.62
    DoubleQuotes
    -0.60
     Infórmanos
    -0.60
    hitting
    -0.60
     resourceCulture
    -0.59
    IsMutable
    -0.58
    POSITIVE LOGITS
     connected
    0.58
     den
    0.57
    utnik
    0.53
     connect
    0.51
    بوابة
    0.50
    connect
    0.49
     connecté
    0.47
    enschutz
    0.47
     Connect
    0.46
    GEBURTSDATUM
    0.45
    Activations Density 0.016%

    No Known Activations