© 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. 13669
    Prev
    Next
    INDEX
    Explanations

    references to confocal microscopy techniques or images

    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
     Attribution
    -1.02
     attribution
    -0.97
    ()");
    -0.87
     myſelf
    -0.85
    SourceChecksum
    -0.84
    رشف
    -0.84
    )");
    
    -0.78
    )");
    -0.75
    rometers
    -0.75
    Attribution
    -0.75
    POSITIVE LOGITS
     confocal
    1.88
     altitude
    0.66
    altitude
    0.64
     enclosing
    0.60
     enclosure
    0.58
    pyx
    0.57
    Altitude
    0.56
    béco
    0.53
     pathlib
    0.52
     enclose
    0.50
    Activations Density 0.002%

    No Known Activations