© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78286
    Prev
    Next
    INDEX
    Explanations

    technical measurements

    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
    Negative Logits
    ✨:
    -0.82
    ArgsConstructor
    -0.68
    __":
    -0.63
    __':
    -0.62
    setEditable
    -0.57
    */)
    -0.57
     blowing
    -0.56
    躇
    -0.56
     dialing
    -0.56
    ']?>
    -0.56
    POSITIVE LOGITS
    angsaan
    0.52
    extAlignment
    0.48
     astore
    0.48
     sco
    0.47
     lounge
    0.47
     lenker
    0.45
    andidaten
    0.45
     twist
    0.44
    localctx
    0.44
    tribune
    0.44
    Activations Density 0.002%

    No Known Activations