© 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. 20-CLT-HP
    7. 77677
    Prev
    Next
    INDEX
    Explanations

    Code, foreign language, phone

    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
    MLLoader
    -0.71
    DeleteBehavior
    -0.66
     VBox
    -0.65
    TintMode
    -0.63
    XMLSchema
    -0.59
    RenderAtEndOf
    -0.58
    Viki
    -0.57
     linkovi
    -0.57
    TargetException
    -0.57
    ofire
    -0.57
    POSITIVE LOGITS
    agad
    0.46
     insuffisamment
    0.42
     conseguenza
    0.42
    ewel
    0.42
    smh
    0.41
    산
    0.40
    akat
    0.38
    一手
    0.38
    mob
    0.38
     insegu
    0.38
    Activations Density 0.001%

    No Known Activations