© 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. 5-CLT-HP
    7. 92768
    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
     Other
    -0.52
    setVerticalGroup
    -0.51
     notably
    -0.49
    ্ল
    -0.49
     deeply
    -0.49
     Particularly
    -0.49
     massive
    -0.48
     Warm
    -0.47
     mostly
    -0.47
     Inspect
    -0.47
    POSITIVE LOGITS
    GHIJKLM
    0.56
     Jefus
    0.53
    mybatisplus
    0.52
    Климат
    0.52
     NSCoder
    0.51
    AxisAlignment
    0.51
     StatefulWidget
    0.50
     Савезне
    0.50
    CodeAttribute
    0.48
    ActionCreators
    0.48
    Activations Density 0.000%

    No Known Activations