© 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. 20-CLT-HP
    7. 72864
    Prev
    Next
    INDEX
    Explanations

    java

    np_max-act-logits · 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
     dignité
    -0.90
     charité
    -0.86
     venons
    -0.81
     pouvoit
    -0.80
     تضيفلها
    -0.79
    IsMutable
    -0.79
     nôtre
    -0.78
     auroit
    -0.77
     الحره
    -0.77
     bonté
    -0.77
    POSITIVE LOGITS
     
    0.36
     b
    0.35
    Géographie
    0.35
    RSpec
    0.34
     mish
    0.34
    odan
    0.33
    cion
    0.33
     las
    0.33
     chou
    0.33
    HtmlAttribute
    0.32
    Activations Density 0.001%

    No Known Activations