© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 490
    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
     ویکی‌آمباردا
    -0.65
    +#+
    -0.64
    OrBuilder
    -0.59
     חיצוניים
    -0.59
    leetcode
    -0.59
     NgModule
    -0.58
    webElementXpaths
    -0.58
    __(/*!
    -0.57
    StructEnd
    -0.56
    ArgumentParser
    -0.55
    POSITIVE LOGITS
     last
    0.54
     mon
    0.53
     Des
    0.49
    docx
    0.49
     Worthy
    0.49
    )|\
    0.48
     Last
    0.47
     res
    0.45
     Tri
    0.45
     性
    0.45
    Activations Density 0.011%

    No Known Activations