© 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. 0-CLT-HP
    7. 93859
    Prev
    Next
    INDEX
    Explanations

    gon

    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
     مرئيه
    -0.81
     cherchés
    -0.79
     autorité
    -0.75
     يتيمه
    -0.75
     esperienza
    -0.74
     émission
    -0.73
     Мексичка
    -0.71
    LookAnd
    -0.70
     snippetHide
    -0.69
     ExecuteAsync
    -0.69
    POSITIVE LOGITS
     battery
    0.56
     portion
    0.56
     few
    0.55
     key
    0.53
     full
    0.51
     significant
    0.51
     lot
    0.50
     plane
    0.50
     mixture
    0.50
     set
    0.50
    Activations Density 0.062%

    No Known Activations