© 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. 92945
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    脚注の使い方
    -0.59
     oprot
    -0.57
     MenuView
    -0.56
     "..\..\
    -0.51
    TintMode
    -0.49
     getLogin
    -0.48
    таратура
    -0.48
    erals
    -0.47
    ค์
    -0.47
     EXPORT
    -0.47
    POSITIVE LOGITS
     становника
    0.57
    ,
    0.56
    I
    0.51
     I
    0.50
    '
    0.50
    
    0.49
    ’
    0.47
    setAccessible
    0.47
     (
    0.46
    XtraEditors
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.