© 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. 4-CLT-HP
    7. 1906
    Prev
    Next
    INDEX
    Explanations

    know

    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
     Мексичка
    -0.94
     تضيفلها
    -0.77
    Dislikes
    -0.75
     وتسجيلات
    -0.74
    出版年
    -0.74
     Wikimedijinoj
    -0.70
     florales
    -0.66
    الدراسه
    -0.66
    AnchorStyles
    -0.66
    queryInterface
    -0.65
    POSITIVE LOGITS
     how
    0.58
     what
    0.47
     that
    0.44
    而言
    0.42
     it
    0.42
    InputTagHelper
    0.41
    deki
    0.40
     balanceOf
    0.40
     MessageBoxIcon
    0.40
     strong
    0.38
    Activations Density 0.031%

    No Known Activations