© 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. 71466
    Prev
    Next
    INDEX
    Explanations

    Technical/academic words

    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
     étoit
    -0.66
     auroit
    -0.64
     poussière
    -0.61
     visibilité
    -0.60
     feroit
    -0.60
     sanitaires
    -0.60
     varandra
    -0.59
     ouvriers
    -0.58
     créativité
    -0.58
     numéros
    -0.56
    POSITIVE LOGITS
     mortality
    0.74
     vitreous
    0.67
    CloseOperation
    0.66
     jurisprudence
    0.65
     equine
    0.65
     counsel
    0.65
     vessel
    0.64
     aqueous
    0.61
     motor
    0.61
     ambulatory
    0.61
    Activations Density 0.000%

    No Known Activations