© 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. 6-RES-MATRYOSHKA-DC
    7. 1172
    Prev
    Next
    INDEX
    Explanations

    references to rules and order

    oai_token-act-pair · gemini-2.0-flash
    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
    endsection
    -0.83
    httphttps
    -0.78
     BoxFit
    -0.77
     resourceCulture
    -0.76
    hasMoreElements
    -0.75
    ьаж
    -0.74
     BorderRadius
    -0.73
     AssemblyProduct
    -0.73
    Seni
    -0.73
     Humphreys
    -0.73
    POSITIVE LOGITS
     rule
    2.33
     rules
    2.27
     Rule
    2.17
     RULE
    2.17
     Rules
    2.16
    Rules
    2.03
    rules
    2.02
     RULES
    1.99
    rule
    1.98
    Rule
    1.95
    Activations Density 0.357%

    No Known Activations