© 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. 5321
    Prev
    Next
    INDEX
    Explanations

    mathematical structures, specifically the special linear group of matrices

    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
    Not in Any Lists

    No Comments

    Negative Logits
    клопе
    -0.95
    mathbb
    -0.80
    !*\
    -0.80
    enumii
    -0.80
    posedge
    -0.78
    TagMode
    -0.78
    MessageOf
    -0.74
    PerformLayout
    -0.72
    AddTagHelper
    -0.72
     raiſ
    -0.71
    POSITIVE LOGITS
    InBackground
    0.50
    ViewFeatures
    0.46
     moi
    0.44
    newInstance
    0.44
     r
    0.44
    عم
    0.44
     and
    0.42
    minHeight
    0.42
     F
    0.42
     kise
    0.41
    Activations Density 0.033%

    No Known Activations