© 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. 7667
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of naturalization or the process of becoming a citizen

    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
     Еще
    -0.66
     neighborhood
    -0.57
     neighborhoods
    -0.54
    ing
    -0.54
     labor
    -0.53
     Favorite
    -0.53
     favored
    -0.53
     favor
    -0.51
    ingt
    -0.50
    ${
    -0.50
    POSITIVE LOGITS
    ization
    2.72
    isation
    2.48
    IZATION
    2.09
    izations
    2.06
    ized
    1.97
    ize
    1.91
    izing
    1.80
    ised
    1.77
    ización
    1.73
    izes
    1.72
    Activations Density 0.152%

    No Known Activations