© 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. 5-CLT-HP
    7. 3372
    Prev
    Next
    INDEX
    Explanations

    K

    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
     रहे
    -0.61
     mesmos
    -0.49
    Untitled
    -0.49
     are
    -0.47
     (
    -0.46
    AspNetCore
    -0.46
     !(
    -0.46
     
    -0.45
    кет
    -0.45
    setUse
    -0.45
    POSITIVE LOGITS
     defaultstate
    0.79
     سكانية
    0.76
    EndGlobalSection
    0.65
    #+#
    0.60
     Chwiliwch
    0.59
    expandindo
    0.58
    awtextra
    0.57
    setVerticalGroup
    0.56
     Roskov
    0.55
     الاطلاع
    0.54
    Activations Density 0.021%

    No Known Activations