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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3107
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Wiktionnaire
    -0.61
    nościo
    -0.54
    انجليز
    -0.53
    ✭✭
    -0.51
     noDo
    -0.50
    mainAxisSize
    -0.45
    worlds
    -0.44
    InteropServices
    -0.44
    rond
    -0.43
    GNUC
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.69
     Majefty
    0.60
    findpost
    0.57
     ſeveral
    0.56
     BoxDecoration
    0.55
    óstico
    0.55
     GenerationType
    0.55
    BackStack
    0.55
     uſe
    0.54
    deutschen
    0.54
    Activations Density 0.013%

    No Known Activations