© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5779
    Prev
    Next
    INDEX
    Explanations

    references to the ary (Aryan or Arythmetic) lineage or context

    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
    sizeCache
    -0.75
    ThroughAttribute
    -0.68
    tagHelperRunner
    -0.55
     تضيفلها
    -0.55
    aarrggbb
    -0.54
    Vidite
    -0.54
    IntoConstraints
    -0.54
    Personendaten
    -0.54
    toPromise
    -0.54
     Mousse
    -0.54
    POSITIVE LOGITS
    ary
    3.94
    ARY
    3.56
    aries
    2.61
     ary
    2.09
    ARIES
    1.98
    arya
    1.95
    arily
    1.77
    arie
    1.70
    Ary
    1.62
     Ary
    1.52
    Activations Density 0.027%

    No Known Activations