© 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. 1486
    Prev
    Next
    INDEX
    Explanations

    references to the abbreviation "ac," likely indicating the word "acet" or related chemical abbreviations

    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
    DataURL
    -0.64
    flashdata
    -0.59
    AccessorTable
    -0.55
     Roskov
    -0.54
     viewType
    -0.53
    Distribuzione
    -0.50
     TextStyle
    -0.50
    ագրություններ
    -0.49
    fillType
    -0.49
    rénées
    -0.48
    POSITIVE LOGITS
    ac
    3.63
    AC
    3.41
     ac
    3.25
     Ac
    3.20
     AC
    3.11
    Ac
    3.05
    acs
    2.20
     acc
    2.08
     Acc
    2.03
     ACCOM
    1.98
    Activations Density 0.428%

    No Known Activations