© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13530
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of algebraically defined mathematical structure

    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
    tically
    -1.39
    atively
    -1.02
    matically
    -0.90
    istically
    -0.77
    ctively
    -0.70
    ologically
    -0.65
    tively
    -0.63
    ticamente
    -0.63
    logically
    -0.59
    copically
    -0.59
    POSITIVE LOGITS
    ically
    1.00
    tics
    0.93
    icals
    0.62
    ICAL
    0.59
    mappedBy
    0.57
    ical
    0.56
    FieldBuilder
    0.54
     '\\;'
    0.54
    optarg
    0.52
    tory
    0.52
    Activations Density 0.002%

    No Known Activations