© 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. 2-RES-MATRYOSHKA-DC
    7. 2524
    Prev
    Next
    INDEX
    Explanations

    references to political authority or figures, especially the term "governor."

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Farah
    -0.54
    бло
    -0.52
     OFDb
    -0.52
    itag
    -0.49
    æk
    -0.49
    ้อง
    -0.46
     saites
    -0.46
     terrest
    -0.45
     संस्
    -0.44
     consultato
    -0.44
    POSITIVE LOGITS
     Governor
    3.69
     governor
    3.67
    Governor
    3.50
     GOVERNOR
    3.19
    governor
    3.09
     governors
    3.00
     Governors
    2.94
     Gov
    2.78
    Gov
    2.66
     gouverneur
    2.36
    Activations Density 0.011%

    No Known Activations