© 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. 9001
    Prev
    Next
    INDEX
    Explanations

    technical 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
    Not in Any Lists

    No Comments

    Negative Logits
     Canto
    -0.79
     canto
    -0.73
     Torre
    -0.70
    Canto
    -0.60
    Torre
    -0.59
     gyrus
    -0.59
    ctrica
    -0.44
    下载附件
    -0.44
    DataSetChanged
    -0.38
     gql
    -0.37
    POSITIVE LOGITS
     defaultstate
    0.81
     itſelf
    0.78
     виправивши
    0.78
    VersionUID
    0.75
     تضيفلها
    0.74
    sidemargin
    0.73
    ſelf
    0.73
    BeginContext
    0.71
     Majefty
    0.71
    Personendaten
    0.70
    Activations Density 0.018%

    No Known Activations