© 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. 4-CLT-HP
    7. 938
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    shortcode
    -0.48
    delle
    -0.46
    igshid
    -0.45
     dica
    -0.45
    ginald
    -0.42
     Im
    -0.42
    ссер
    -0.41
     IM
    -0.41
    ViewImports
    -0.40
     vie
    -0.40
    POSITIVE LOGITS
    esis
    1.00
    ESIS
    0.73
    esi
    0.71
    hesis
    0.64
    eses
    0.59
    AndroidJUnit
    0.59
    IUrlHelper
    0.59
     otomatig
    0.57
    :✨
    0.57
    esy
    0.56
    Activations Density 0.067%

    No Known Activations