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. 20-CLT-HP
    4. 74059
    Prev
    Next
    INDEX
    Explanations

    ex

    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
    FormTagHelper
    -0.57
    IBarButtonItem
    -0.56
    MLLoader
    -0.56
    yntaxException
    -0.54
    abetes
    -0.52
     صوتيه
    -0.52
    Biographie
    -0.52
    tableFuture
    -0.52
    ChildScrollView
    -0.51
    ביוגרפיה
    -0.49
    POSITIVE LOGITS
     transfieras
    0.60
     Nih
    0.54
    hale
    0.54
     StatefulWidget
    0.54
    cla
    0.53
    loài
    0.51
    Gweler
    0.51
     Mach
    0.51
    ude
    0.49
     nih
    0.49
    Activations Density 0.006%

    No Known Activations