© 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. 77982
    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
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیای
    -0.70
     propOrder
    -0.63
    KommentareTeilen
    -0.61
     насељу
    -0.60
     ویکی‌آمباردا
    -0.59
    السكان
    -0.58
    IonicModule
    -0.56
    клопе
    -0.56
    }}/>
    -0.56
    >*/
    -0.54
    POSITIVE LOGITS
    naden
    0.49
    mento
    0.44
    lon
    0.41
    mbolo
    0.41
    mä
    0.39
    opsida
    0.39
    เพ
    0.39
    po
    0.39
    nads
    0.38
    焼
    0.38
    Activations Density 0.002%

    No Known Activations