© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14850
    Prev
    Next
    INDEX
    Explanations

    references to specific product categories or types

    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
     Anti
    -0.45
    <eos>
    -0.41
     lla
    -0.41
     R
    -0.40
     T
    -0.40
    是一
    -0.40
    вин
    -0.40
    di
    -0.38
     DR
    -0.38
     Multi
    -0.38
    POSITIVE LOGITS
    SourceChecksum
    1.06
     Destinations
    1.05
     Strains
    1.04
     Bins
    1.00
     Fields
    0.99
     Hobbies
    0.99
     Formats
    0.98
     Viruses
    0.98
     Fabrics
    0.96
     Devices
    0.96
    Activations Density 0.183%

    No Known Activations