© 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. 1-CLT-HP
    7. 15847
    Prev
    Next
    INDEX
    Explanations

    red

    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
    setVerticalGroup
    -0.83
     فريبيس
    -0.74
     oprot
    -0.70
     rouges
    -0.69
     reds
    -0.67
    exitRule
    -0.63
    ]--;
    -0.63
    WindowConstants
    -0.63
     red
    -0.62
     roja
    -0.62
    POSITIVE LOGITS
     typelib
    0.42
     SqlCommand
    0.42
    ristor
    0.41
    EMP
    0.41
    िक्ष
    0.40
     Me
    0.40
     ME
    0.39
    冀
    0.39
    AspNetCore
    0.38
    kish
    0.37
    Activations Density 0.031%

    No Known Activations