© 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. 7492
    Prev
    Next
    INDEX
    Explanations

    references to spectral analysis techniques and data

    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
     MatDialog
    -0.76
    didSet
    -0.68
     nargin
    -0.67
    inquirer
    -0.61
     algemeen
    -0.61
     jsPsych
    -0.60
     rospy
    -0.60
    发表于
    -0.59
     mariée
    -0.58
     {?}
    -0.56
    POSITIVE LOGITS
     cref
    0.64
    ustra
    0.60
     statistics
    0.60
     stats
    0.59
     charts
    0.58
    stats
    0.55
     standings
    0.55
     photos
    0.54
    ReusableCell
    0.54
     ویکی‌پدی
    0.53
    Activations Density 0.958%

    No Known Activations