© 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. 6700
    Prev
    Next
    INDEX
    Explanations

    sequences of numeric and symbolic patterns, such as variation annotations or data labels

    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
     IL
    -0.70
    IL
    -0.64
     interleukin
    -0.64
     Il
    -0.56
     il
    -0.56
    il
    -0.54
    Il
    -0.54
    leukin
    -0.49
    BeginContext
    -0.48
    check
    -0.45
    POSITIVE LOGITS
     tartalomajánló
    0.98
     مشين
    0.86
    UnsafeEnabled
    0.86
     ProductService
    0.79
    writeField
    0.75
     kasarigan
    0.75
    modity
    0.74
    brium
    0.73
    saraba
    0.73
    Rohy
    0.72
    Activations Density 0.037%

    No Known Activations