© 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. 0-CLT-HP
    7. 43954
    Prev
    Next
    INDEX
    Explanations

    academic/legal/medical texts

    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
     Bans
    -0.54
    ronyms
    -0.51
    supset
    -0.50
    tor
    -0.48
    hoven
    -0.48
    gapa
    -0.44
    aby
    -0.44
    Bans
    -0.43
    lüğ
    -0.42
     ISSN
    -0.42
    POSITIVE LOGITS
     jadx
    0.69
    出版年
    0.66
     تضيفلها
    0.60
    ANDUM
    0.58
    MLLoader
    0.58
     թվական
    0.58
     SEDS
    0.58
    IVEREF
    0.58
     Ibis
    0.57
     ujednoznacz
    0.57
    Activations Density 1.451%

    No Known Activations