© 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. 5564
    Prev
    Next
    INDEX
    Explanations

    provide

    np_max-act · 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
    +#+
    -0.67
     you
    -0.63
     незавершена
    -0.60
    you
    -0.57
     você
    -0.56
    CGRectMake
    -0.56
    checkable
    -0.55
    twimg
    -0.54
    __',
    -0.54
     utilisons
    -0.53
    POSITIVE LOGITS
    expandindo
    0.54
    plusplus
    0.52
     समीक्षाओं
    0.52
    RUnlock
    0.52
     فريبيس
    0.50
     as
    0.50
     viewDidLoad
    0.49
    Hentet
    0.48
    setAlignment
    0.47
    AlterField
    0.46
    Activations Density 0.002%

    No Known Activations