© 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. 71408
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
     Paglinawan
    -0.54
     Inspections
    -0.53
     Fore
    -0.49
    NTIS
    -0.48
    ciller
    -0.47
     Hust
    -0.47
     TextAlign
    -0.46
     Farms
    -0.46
    zA
    -0.45
     ***!
    -0.45
    POSITIVE LOGITS
     strong
    0.68
    Strong
    0.63
     risk
    0.63
     laude
    0.60
     goede
    0.57
     AssemblyTitle
    0.57
     disambiguazione
    0.57
    strong
    0.57
    Statistiche
    0.56
    iffa
    0.56
    Activations Density 0.002%

    No Known Activations