© 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. 16206
    Prev
    Next
    INDEX
    Explanations

    Brethren

    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
     démocr
    -0.79
     hâte
    -0.77
     manquer
    -0.76
     juridiques
    -0.75
     financières
    -0.71
     énergé
    -0.69
     mourir
    -0.68
     كومونز
    -0.68
     larmes
    -0.66
     religieuses
    -0.66
    POSITIVE LOGITS
    featureID
    0.54
    posedge
    0.52
    ing
    0.52
    s
    0.52
    iata
    0.52
    resave
    0.50
    ging
    0.49
     NSCoder
    0.48
    мка
    0.47
    Contours
    0.47
    Activations Density 0.012%

    No Known Activations