© 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. 20-CLT-HP
    7. 73167
    Prev
    Next
    INDEX
    Explanations

    technical/code related text

    np_max-act-logits · 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
     Moura
    -0.54
    xane
    -0.48
    Enlaces
    -0.48
     uric
    -0.47
    ﾟ)
    -0.46
     gum
    -0.46
     glycol
    -0.46
     Eink
    -0.45
     remission
    -0.45
     urethra
    -0.44
    POSITIVE LOGITS
    rungsseite
    0.91
    ThroughAttribute
    0.73
    脚注の使い方
    0.68
    PreferredItem
    0.67
    ("")]
    0.62
    
    0.61
    bacillus
    0.60
    InputBorder
    0.59
    sidemargin
    0.57
    /*---
    0.54
    Activations Density 0.000%

    No Known Activations