© 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. 92339
    Prev
    Next
    INDEX
    Explanations

    wave

    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
     spéciaux
    -0.70
    endphp
    -0.68
    ⓧ
    -0.60
     rencontr
    -0.59
     @}
    -0.59
     relatifs
    -0.58
    igenschaften
    -0.58
     Agr
    -0.58
    timewa
    -0.57
     abandonné
    -0.55
    POSITIVE LOGITS
     therapy
    0.61
     exercise
    0.56
     routine
    0.56
     workout
    0.55
     meditation
    0.54
     الرياضيه
    0.53
     training
    0.52
     involves
    0.50
     technique
    0.49
     Chré
    0.48
    Activations Density 0.000%

    No Known Activations