© 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. 71341
    Prev
    Next
    INDEX
    Explanations

    deficiencies/medical issues

    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
    mybatisplus
    -1.02
    AndEndTag
    -0.74
     kasarigan
    -0.71
    脚注の使い方
    -0.68
     pinulongan
    -0.68
     iArr
    -0.68
     ReactDOM
    -0.68
    +#+#
    -0.67
    URLException
    -0.64
    ViewImports
    -0.63
    POSITIVE LOGITS
     wasting
    0.54
     st
    0.52
     under
    0.49
     wasted
    0.47
     acute
    0.46
     Acute
    0.46
     Stu
    0.44
     Und
    0.43
     SAM
    0.43
     Under
    0.43
    Activations Density 0.001%

    No Known Activations