© 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. 10783
    Prev
    Next
    INDEX
    Explanations

    references to combinatorial concepts or methods

    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
     Coleman
    -0.98
    Coleman
    -0.88
    InitVars
    -0.59
     lenker
    -0.57
     contextLoads
    -0.57
     BorderSide
    -0.54
     suena
    -0.54
     preferential
    -0.54
     Justo
    -0.54
     australis
    -0.52
    POSITIVE LOGITS
     combinatorial
    2.39
     Combin
    1.69
     combin
    1.49
    combin
    1.16
    Combin
    1.13
     Dalton
    1.02
    Dalton
    0.79
     يتيمه
    0.75
     Lancaster
    0.63
    Tikang
    0.62
    Activations Density 0.006%

    No Known Activations