© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14578
    Prev
    Next
    INDEX
    Explanations

    {

    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
    ckel
    -1.87
    DotNetBar
    -0.73
    InputBorder
    -0.72
    AddTagHelper
    -0.68
     FontWeight
    -0.67
    évaluateur
    -0.67
    bootstrapcdn
    -0.65
    ChildScrollView
    -0.65
    TagMode
    -0.64
     SqlParameter
    -0.63
    POSITIVE LOGITS
    class
    0.49
     ویکی‌پدی
    0.47
    bean
    0.45
    bag
    0.43
    assination
    0.43
     compleanno
    0.42
    stun
    0.42
    bound
    0.42
    mary
    0.41
    bow
    0.41
    Activations Density 0.037%

    No Known Activations