© 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. 7536
    Prev
    Next
    INDEX
    Explanations

    references to statistical tests and measures

    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
    mybatisplus
    -0.65
    पया
    -0.59
     Coe
    -0.59
    findpost
    -0.58
     techniczne
    -0.57
     marins
    -0.57
     вікі
    -0.57
     Cathy
    -0.56
    hdessä
    -0.56
    帖最后由
    -0.55
    POSITIVE LOGITS
     chi
    3.30
     Chi
    3.03
    Chi
    2.91
    chi
    1.93
     CHI
    1.78
    CHI
    1.63
    chir
    1.49
    Chir
    1.49
    chim
    1.44
     chisel
    1.38
    Activations Density 0.016%

    No Known Activations