© 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. 1-CLT-HP
    7. 8866
    Prev
    Next
    INDEX
    Explanations

    gain

    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
    Negative Logits
    djangoproject
    -0.68
    apart
    -0.54
     disambiguazione
    -0.53
     lượng
    -0.52
     apart
    -0.51
    verwijspagina
    -0.48
     disponibilités
    -0.46
     solitario
    -0.45
     ​​
    -0.45
    Apart
    -0.45
    POSITIVE LOGITS
     الحره
    0.69
    richTextPanel
    0.66
     TestBed
    0.63
    GEBURTSDATUM
    0.59
    Morfologia
    0.58
    uxxxx
    0.57
    providedIn
    0.56
     Respectfully
    0.56
    rungsseite
    0.56
    SizeF
    0.55
    Activations Density 0.050%

    No Known Activations