© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41885
    Prev
    Next
    INDEX
    Explanations

    Model

    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
     of
    -0.95
    model
    -0.77
    Model
    -0.71
     model
    -0.69
    ของ
    -0.63
     Model
    -0.62
     của
    -0.59
    getModel
    -0.54
     modèle
    -0.52
     της
    -0.51
    POSITIVE LOGITS
    ConstraintMaker
    0.62
     Majefty
    0.60
    TagHelper
    0.58
    Související
    0.57
    led
    0.56
    一动
    0.56
    matically
    0.52
    LEGGI
    0.52
    🏻
    0.52
    Дереккөздер
    0.50
    Activations Density 0.035%

    No Known Activations