© 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. 5-CLT-HP
    7. 92664
    Prev
    Next
    INDEX
    Explanations

    crossing and technical

    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
    WriteTagHelper
    -0.47
    anthin
    -0.47
    AccessorTable
    -0.46
    MessageTagHelper
    -0.45
    illoma
    -0.44
    gwin
    -0.43
    didReceive
    -0.42
    gabung
    -0.41
    IOLOGY
    -0.41
    ństwo
    -0.40
    POSITIVE LOGITS
    sizeCache
    0.74
    Izvori
    0.61
     Threshold
    0.60
    queryInterface
    0.59
    ViewImports
    0.57
     thresholds
    0.57
    ListBy
    0.57
    :✨
    0.57
    StreetMap
    0.57
     nakalista
    0.56
    Activations Density 0.002%

    No Known Activations