© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14468
    Prev
    Next
    INDEX
    Explanations

    references to a specific object or property related to storage or message handling in procedural or code contexts

    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
    ↵↵
    -0.56
    ,
    -0.54
    Clear
    -0.53
    clear
    -0.52
    Poc
    -0.50
    .
    -0.50
     
    -0.49
     period
    -0.49
    (
    -0.48
     You
    -0.47
    POSITIVE LOGITS
     незавершена
    0.92
     ویکی‌پدیا
    0.87
     विश्वसनीयता
    0.87
     חיצוניים
    0.85
    __(/*!
    0.85
    ंदीखरीदारी
    0.85
     مشين
    0.84
     Roskov
    0.84
    IBOutlet
    0.83
     disambiguazione
    0.83
    Activations Density 0.041%

    No Known Activations