© 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. 0-RES-MATRYOSHKA-DC
    7. 10670
    Prev
    Next
    INDEX
    Explanations

    patterns indicating mathematical or logical equivalences

    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
    }}{(
    -0.91
    _{[
    -0.88
    }{(
    -0.83
    }_{(
    -0.79
    BagConstraints
    -0.71
    {-
    -0.68
    BeginInit
    -0.64
     transfieras
    -0.64
    BagLayout
    -0.60
    )}{(
    -0.58
    POSITIVE LOGITS
    _{(
    1.50
     SEDS
    0.61
     dipende
    0.56
     officiel
    0.55
    layın
    0.54
    тябрь
    0.53
     linkovi
    0.53
     vapeur
    0.52
     cland
    0.52
     Arhivirano
    0.52
    Activations Density 0.001%

    No Known Activations