© 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. 71485
    Prev
    Next
    INDEX
    Explanations

    Code and website content

    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
    MessageOf
    -0.93
     estimés
    -0.91
    Rhestr
    -0.80
    出版年
    -0.77
    ResponseWriter
    -0.77
    Abitanti
    -0.75
     विश्वसनीयता
    -0.75
    ArrowToggle
    -0.74
     bezeichneter
    -0.73
     disambiguazione
    -0.69
    POSITIVE LOGITS
    \}\\
    0.38
    НС
    0.37
     tilf
    0.36
    bbene
    0.35
    welijk
    0.35
    vč
    0.35
    aguer
    0.34
    ذك
    0.33
     mignon
    0.33
    webe
    0.33
    Activations Density 0.000%

    No Known Activations