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. 12852
    Prev
    Next
    INDEX
    Explanations

    Dashes

    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
    存于互联网档案馆
    -0.68
     and
    -0.65
    terase
    -0.54
    apimachinery
    -0.52
    heureusement
    -0.52
    RTEX
    -0.51
    /***/
    -0.50
     onAnimation
    -0.48
     catég
    -0.47
    讐
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.64
     aceptas
    0.62
     Presence
    0.53
     Founders
    0.52
    PreferredItem
    0.52
    unknownFields
    0.52
     Publisher
    0.51
    ViewFeatures
    0.50
     Diſ
    0.49
     Managing
    0.48
    Activations Density 0.003%

    No Known Activations