© 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. 71477
    Prev
    Next
    INDEX
    Explanations

    Random text snippets

    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
     myſelf
    -0.75
     للاسماء
    -0.73
     AssemblyTitle
    -0.70
     Efq
    -0.68
    原始内容存档于
    -0.68
     itſelf
    -0.68
     raiſ
    -0.67
     RestTemplate
    -0.66
     surla
    -0.65
     purpoſe
    -0.64
    POSITIVE LOGITS
    lamation
    0.39
    messageInfo
    0.39
    íncipe
    0.39
    PAIGN
    0.37
    commodations
    0.37
    Magdalena
    0.36
    تما
    0.36
    roslav
    0.35
    cination
    0.34
    FON
    0.34
    Activations Density 0.007%

    No Known Activations