© 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. 1-RES-MATRYOSHKA-DC
    7. 1211
    Prev
    Next
    INDEX
    Explanations

    references to specific numbered articles, documents, or cases

    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
    aaaaaaaa
    -0.77
    bø
    -0.75
     Bly
    -0.73
     Goldie
    -0.72
    webElementXpaths
    -0.71
    χρι
    -0.69
     hjemme
    -0.68
     Cly
    -0.68
    jsdelivr
    -0.68
     TextAlign
    -0.67
    POSITIVE LOGITS
     an
    2.66
     An
    1.99
    An
    1.95
     AN
    1.61
    an
    1.58
    AN
    1.11
     anz
    1.07
     anex
    1.05
     aan
    1.02
     Anwar
    0.96
    Activations Density 0.466%

    No Known Activations