© 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. 15682
    Prev
    Next
    INDEX
    Explanations

    patterns involving vertical bar symbols, indicating a focus on symbolic or structural features in the data

    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
    oa̍t
    -1.03
     Мексичка
    -0.97
    AddTagHelper
    -0.95
     ComVisible
    -0.93
     Réponses
    -0.89
     "..\..\..\
    -0.82
    errHandler
    -0.78
     '\\;'
    -0.77
    oredCriteria
    -0.77
    Personensuche
    -0.76
    POSITIVE LOGITS
     \|
    1.92
     mas
    0.52
    WebApplication
    0.50
     cash
    0.50
    鑑
    0.49
    cash
    0.48
    ↗
    0.48
    ́
    0.47
     …
    0.45
    kusi
    0.45
    Activations Density 0.001%

    No Known Activations