© 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. 13428
    Prev
    Next
    INDEX
    Explanations

    references to specific articles, documents, or identifiers that often include the word "a" and are used to specify particular entities or items within a text

    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
     the
    -0.84
     The
    -0.76
     an
    -0.70
     "
    -0.66
     as
    -0.63
     
    -0.62
     for
    -0.60
     from
    -0.59
     in
    -0.58
     “
    -0.57
    POSITIVE LOGITS
    +#+#
    0.97
    IntoConstraints
    0.94
     propOrder
    0.91
     समीक्षाएं
    0.91
     cherchés
    0.89
    MessageTagHelper
    0.88
    OrNil
    0.87
    PerformLayout
    0.86
    ThroughAttribute
    0.84
     AssemblyCompany
    0.84
    Activations Density 0.159%

    No Known Activations