© 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. 7636
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals who previously held notable official positions

    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
     again
    -0.64
     already
    -0.61
     preventivo
    -0.60
     formation
    -0.56
    HasAnnotation
    -0.55
     repeated
    -0.52
     repeat
    -0.52
     Вікіпе
    -0.50
     Again
    -0.50
     AssemblyCulture
    -0.49
    POSITIVE LOGITS
     former
    3.00
    Former
    2.94
     Former
    2.83
    former
    2.64
     ehemalige
    2.05
     ehemaligen
    2.00
     mantan
    1.70
     býval
    1.62
     ehemal
    1.58
     Formerly
    1.48
    Activations Density 0.017%

    No Known Activations