© 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. 1527
    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
    
    -1.08
    adaptiveStyles
    -0.94
    LayoutStyle
    -0.90
    RenderAtEndOf
    -0.87
     unknownFields
    -0.86
     betweenstory
    -0.81
    BeginContext
    -0.79
    Begriffsklä
    -0.79
    ResumeLayout
    -0.74
    DotNetBar
    -0.72
    POSITIVE LOGITS
    baldi
    0.49
     Shore
    0.44
    alama
    0.43
    집
    0.43
     бри
    0.41
     للمعارف
    0.41
    atov
    0.41
    chus
    0.40
     Ball
    0.39
     X
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.