© 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. 3-RES-MATRYOSHKA-DC
    7. 3056
    Prev
    Next
    INDEX
    Explanations

    the word "scan" in the context of data acquisition or image processing

    oai_token-act-pair · gemini-2.0-flash
    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
     SEDS
    -0.65
    tvguidetime
    -0.62
    Havolalar
    -0.61
    таратура
    -0.61
    atory
    -0.59
     pâte
    -0.59
    oplayer
    -0.59
     Hildebrand
    -0.59
     bouch
    -0.58
    orde
    -0.57
    POSITIVE LOGITS
     scan
    3.05
     Scan
    2.77
    scan
    2.75
     scanning
    2.67
    Scan
    2.61
     scans
    2.58
     scanned
    2.50
     SCAN
    2.42
    scanning
    2.34
     Scanning
    2.28
    Activations Density 0.017%

    No Known Activations