© 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. 0-RES-MATRYOSHKA-DC
    7. 11210
    Prev
    Next
    INDEX
    Explanations

    references to configuration files or filenames, specifically filtering for variations in file paths, list structures, or related tokens

    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
     ujednoznacz
    -0.76
    ⓧ
    -0.69
    ंदीखरीदारी
    -0.64
    verwijspagina
    -0.59
     por
    -0.58
    Зноскі
    -0.57
     penge
    -0.56
    MemoryWarning
    -0.56
    kese
    -0.54
    enste
    -0.54
    POSITIVE LOGITS
     toim
    3.84
    toim
    1.60
     toimi
    1.00
     toiminta
    0.66
     Suom
    0.63
     piaggio
    0.60
     Zanzibar
    0.59
     مشارکت‌کنندگان
    0.59
     Ioan
    0.58
     mues
    0.58
    Activations Density 0.009%

    No Known Activations