© 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. 8800
    Prev
    Next
    INDEX
    Explanations

    minister

    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
     betweenstory
    -0.71
     indépendante
    -0.61
     cherchés
    -0.59
    menden
    -0.56
    scribers
    -0.54
    ="@+
    -0.54
     mauvaises
    -0.54
    JspWriter
    -0.53
     noires
    -0.52
     Obre
    -0.52
    POSITIVE LOGITS
     secondly
    0.59
    astify
    0.57
    Diwedd
    0.54
    zzled
    0.52
     anywhere
    0.51
    ised
    0.49
     quickly
    0.49
     AssemblyCulture
    0.48
     accessory
    0.48
     the
    0.48
    Activations Density 0.135%

    No Known Activations