© 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. 6-RES-MATRYOSHKA-DC
    7. 1427
    Prev
    Next
    INDEX
    Explanations

    references to legal cases

    oai_token-act-pair · gemini-2.0-flash
    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
    MigrationBuilder
    -0.58
    rano
    -0.53
    ValueStyle
    -0.48
    soi
    -0.47
    ra
    -0.47
    Tembelea
    -0.46
    antu
    -0.46
     fini
    -0.46
    жко
    -0.45
     Fly
    -0.45
    POSITIVE LOGITS
    Supp
    1.73
     Supp
    1.70
    supp
    1.54
    setlength
    1.34
     supp
    1.30
     fupp
    0.88
     suppression
    0.88
     Suppression
    0.85
     suppress
    0.85
     suppressor
    0.84
    Activations Density 0.120%

    No Known Activations