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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14883
    Prev
    Next
    INDEX
    Explanations

    references to an approach or method that simplifies or approximates complex models or computations

    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
     '\\;'
    -0.97
    awtextra
    -0.96
     <<<<<<<<<<<<<<
    -0.93
     EconPapers
    -0.89
    posedge
    -0.85
     مرئيه
    -0.79
    SuccessListener
    -0.78
    ChildScrollView
    -0.77
    RectangleBorder
    -0.77
    IUrlHelper
    -0.75
    POSITIVE LOGITS
     simplified
    2.56
     Simplified
    2.14
    simplified
    1.97
    Simplified
    1.84
     simplification
    1.65
     simpli
    1.23
     simplif
    1.15
     simplifying
    1.13
     simplify
    1.08
     упро
    1.02
    Activations Density 0.002%

    No Known Activations