© 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. 0-CLT-HP
    7. 95670
    Prev
    Next
    INDEX
    Explanations

    attack

    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
    脚注の使い方
    -0.98
     betweenstory
    -0.96
    ſelf
    -0.94
    ſelves
    -0.93
     itſelf
    -0.91
     للمعارف
    -0.90
     purpoſe
    -0.90
     الحره
    -0.86
     Anſ
    -0.83
    Datuak
    -0.83
    POSITIVE LOGITS
     
    0.74
    ↵↵
    0.60
     C
    0.60
     "
    0.59
    ↵
    0.57
    jfree
    0.56
    .
    0.55
    ,
    0.52
    vē
    0.51
     and
    0.50
    Activations Density 0.069%

    No Known Activations