© 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. 2615
    Prev
    Next
    INDEX
    Explanations

    references to the type and size of quantities or categories

    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
     
    -0.53
     You
    -0.49
    рони
    -0.49
    ↵↵
    -0.48
     “
    -0.47
    TabIndex
    -0.47
     dan
    -0.47
     giác
    -0.46
    makedirs
    -0.46
    waarde
    -0.46
    POSITIVE LOGITS
     ویکی‌پدیای
    1.03
     crdi
    0.89
     purpoſe
    0.88
     Efq
    0.88
     itſelf
    0.88
    SharedDtor
    0.88
    theless
    0.87
     Jefus
    0.86
     myſelf
    0.86
     ſtate
    0.85
    Activations Density 0.670%

    No Known Activations