© 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. 16233
    Prev
    Next
    INDEX
    Explanations

    code and errors

    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
    nock
    -1.50
     Statute
    -0.75
    webElementXpaths
    -0.49
     Sketch
    -0.46
     sketch
    -0.42
    sketch
    -0.42
    sk
    -0.42
    hit
    -0.40
     []),
    -0.40
    Sk
    -0.40
    POSITIVE LOGITS
    tvguidetime
    0.76
    ########.
    0.76
    AndEndTag
    0.75
     Wikispecies
    0.74
    IsContent
    0.74
     للمعارف
    0.74
     ویکی‌پدی
    0.73
    脚注の使い方
    0.69
    +#+
    0.68
     CURIAM
    0.68
    Activations Density 0.735%

    No Known Activations