© 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. 2-RES-MATRYOSHKA-DC
    7. 6853
    Prev
    Next
    INDEX
    Explanations

    references to specific structured data elements, such as measurements, gene lists, or coding sequences in scientific 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
     vecin
    -0.56
    CGRectMake
    -0.55
    addGap
    -0.55
    IndentedString
    -0.54
    closedir
    -0.52
     MaterialApp
    -0.52
    もと
    -0.52
     affari
    -0.51
     недель
    -0.50
    addPreferredGap
    -0.50
    POSITIVE LOGITS
    ArrowToggle
    0.65
     Paglinawan
    0.62
    windowFixed
    0.56
    Démographie
    0.55
     незавершена
    0.54
     disponibilités
    0.54
     gynhyrchwyd
    0.54
    Carriera
    0.53
     typelib
    0.53
     désolés
    0.52
    Activations Density 1.130%

    No Known Activations