© 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. 16014
    Prev
    Next
    INDEX
    Explanations

    instructions/explanations

    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
     myſelf
    -1.30
     itſelf
    -1.22
    ſelves
    -1.20
     himſelf
    -1.08
     themſelves
    -1.05
     Italijanski
    -1.04
     Theſe
    -1.04
    Autoritní
    -1.04
     theſe
    -1.02
     ſeveral
    -1.02
    POSITIVE LOGITS
     
    0.60
     (
    0.58
    ↵
    0.54
      
    0.52
     a
    0.50
    ,
    0.49
    ↵↵
    0.48
     T
    0.47
     E
    0.47
    :
    0.46
    Activations Density 0.009%

    No Known Activations