© 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. 1-RES-MATRYOSHKA-DC
    7. 52
    Prev
    Next
    INDEX
    Explanations

    references to HTML table elements and related structural tags

    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
     kokos
    -0.55
     éclair
    -0.53
     héro
    -0.52
     princesse
    -0.52
    Handlung
    -0.51
     ujarnya
    -0.50
    randn
    -0.50
     religieux
    -0.50
    日语
    -0.50
     produjo
    -0.49
    POSITIVE LOGITS
     table
    4.59
    table
    4.19
     Table
    4.19
    Table
    3.98
     tables
    3.84
    TABLE
    3.56
     TABLE
    3.52
     Tables
    3.45
    tables
    3.20
    Tables
    3.02
    Activations Density 1.701%

    No Known Activations