© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 348
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships between concepts or variables

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    帖最后由
    -0.93
     <<<<<<<<<<<<<<
    -0.84
    تقاوى
    -0.83
     Савезне
    -0.83
    
    -0.73
    devamını
    -0.71
    principalColumn
    -0.70
     Infórmanos
    -0.70
     otomatig
    -0.70
    uxxxx
    -0.69
    POSITIVE LOGITS
     the
    0.79
     fact
    0.49
     Tatsache
    0.43
     a
    0.42
     Italij
    0.42
     việc
    0.42
     esprits
    0.41
     pendapat
    0.41
     táctil
    0.41
     jagung
    0.39
    Activations Density 5.255%

    No Known Activations