© 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. 0-CLT-HP
    7. 42861
    Prev
    Next
    INDEX
    Explanations

    medicine/science

    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
     blessés
    -0.68
     enfans
    -0.65
     preuves
    -0.63
     ucapnya
    -0.62
     réfugiés
    -0.61
     sièges
    -0.60
     âmes
    -0.60
     journalistes
    -0.60
     respectivos
    -0.59
     fédé
    -0.59
    POSITIVE LOGITS
    <bos>
    0.78
     referenties
    0.60
    ↵↵
    0.59
    localctx
    0.59
    blood
    0.59
     blood
    0.56
     anemia
    0.56
    noid
    0.56
    binant
    0.55
     sapiens
    0.55
    Activations Density 0.102%

    No Known Activations