© 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. 12-RES-MATRYOSHKA-DC
    7. 25439
    Prev
    Next
    INDEX
    Explanations

    references to nobility and titles, specifically "Duke" and related terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    Anand
    -0.78
     Hollis
    -0.74
     aéri
    -0.71
    aryen
    -0.71
     préfé
    -0.69
    Lydia
    -0.69
     Kenney
    -0.69
    Selen
    -0.68
     Kars
    -0.67
     Anand
    -0.66
    POSITIVE LOGITS
     Duke
    1.60
    Duke
    1.47
     DUKE
    1.30
     Dukes
    1.29
     duke
    1.19
     Duque
    0.96
     Durham
    0.95
     Ellington
    0.90
     Duchess
    0.87
    duke
    0.84
    Activations Density 0.011%

    No Known Activations