© 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. 10449
    Prev
    Next
    INDEX
    Explanations

    a

    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
     nahilalakip
    -0.72
     myſelf
    -0.69
    contentLoaded
    -0.68
     himſelf
    -0.66
    providedIn
    -0.66
     cohomology
    -0.63
     betweenstory
    -0.61
     whoſe
    -0.60
    انيف
    -0.60
    rowable
    -0.60
    POSITIVE LOGITS
     couple
    0.71
     few
    0.71
     Few
    0.61
    addPreferredGap
    0.60
     Couple
    0.57
     ton
    0.56
     lot
    0.55
    lot
    0.54
     bit
    0.53
    Few
    0.53
    Activations Density 0.007%

    No Known Activations