© 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. 374
    Prev
    Next
    INDEX
    Explanations

    dialogue and expressions of authority in conversation

    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
    twimg
    -0.81
     ujednoznacz
    -0.74
    expandindo
    -0.71
    ChildScrollView
    -0.68
     snippetHide
    -0.67
    舺
    -0.65
    تقاوى
    -0.64
    
    -0.60
    بوابة
    -0.59
     ErrIntOverflow
    -0.59
    POSITIVE LOGITS
    ScopeManager
    0.36
     answer
    0.35
    Answer
    0.34
     asked
    0.32
     whose
    0.31
     épaules
    0.31
     carteira
    0.30
     Tienes
    0.30
     secas
    0.28
     tæn
    0.28
    Activations Density 1.046%

    No Known Activations