© 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. 1-CLT-HP
    7. 13962
    Prev
    Next
    INDEX
    Explanations

    view

    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
     view
    -0.59
    bootstrapcdn
    -0.58
     GenerationType
    -0.56
     initComponents
    -0.56
     bağlantılar
    -0.55
     View
    -0.54
    utilisons
    -0.53
     klien
    -0.53
     vícti
    -0.52
    MigrationBuilder
    -0.52
    POSITIVE LOGITS
    FXMLLoader
    0.57
    InstanceState
    0.53
    ynthetic
    0.52
    ecuzione
    0.50
    quip
    0.50
     kry
    0.48
    IDENTAL
    0.48
     synthase
    0.48
    bella
    0.47
    ☸
    0.47
    Activations Density 0.012%

    No Known Activations