© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14056
    Prev
    Next
    INDEX
    Explanations

    the term "comparator" or its variants

    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
     Вікіпе
    -0.74
    τέλε
    -0.72
    tagHelperRunner
    -0.70
     FetchType
    -0.66
    MLLoader
    -0.66
     onOptions
    -0.66
    iprot
    -0.65
    GEBURTS
    -0.65
     Signalez
    -0.64
    localctx
    -0.64
    POSITIVE LOGITS
     comparator
    0.90
    oton
    0.71
    otex
    0.68
    laub
    0.66
     mell
    0.65
    SND
    0.65
     Kui
    0.63
    cola
    0.63
     Piazza
    0.63
     DIO
    0.62
    Activations Density 0.066%

    No Known Activations