© 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. 1-RES-MATRYOSHKA-DC
    7. 1377
    Prev
    Next
    INDEX
    Explanations

    references to simple, straightforward, and user-friendly descriptions of products or solutions

    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
    AddTagHelper
    -0.76
    !*\
    -0.68
    ColumnHeader
    -0.66
     تانيه
    -0.64
    besondere
    -0.60
     tfsi
    -0.60
    хьтан
    -0.60
     fondament
    -0.58
     cometh
    -0.57
     فريبيس
    -0.57
    POSITIVE LOGITS
     easy
    4.28
    easy
    3.97
    Easy
    3.86
     Easy
    3.78
     easily
    3.56
     EASY
    3.47
    EASY
    3.34
    easily
    3.33
     easier
    3.25
     fácil
    3.11
    Activations Density 0.257%

    No Known Activations