© 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. 7412
    Prev
    Next
    INDEX
    Explanations

    references to relatives, especially siblings and nephews

    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
     AssemblyCulture
    -0.69
    enumi
    -0.64
    ttino
    -0.64
     Lasso
    -0.62
     recyclerView
    -0.62
    culadora
    -0.61
    genheim
    -0.60
     defaultdict
    -0.60
    BeginContext
    -0.60
    NameInMap
    -0.59
    POSITIVE LOGITS
     brother
    2.72
     Brother
    2.70
    Brother
    2.66
     brothers
    2.56
    brother
    2.55
     BROTHER
    2.52
     Brothers
    2.41
     sister
    2.34
     Sister
    2.34
    brothers
    2.31
    Activations Density 0.034%

    No Known Activations