© 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. 3292
    Prev
    Next
    INDEX
    Explanations

    references to lithography, including related terminology about patterns, equipment, and processes used in lithography

    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
    saraba
    -0.54
    レスト
    -0.49
    ほ
    -0.49
     rest
    -0.47
    Enders
    -0.47
    ьа
    -0.45
     Eins
    -0.45
    Witam
    -0.44
    ListItemIcon
    -0.44
     Neub
    -0.43
    POSITIVE LOGITS
    ography
    3.27
    ographic
    2.53
    graphy
    2.20
    graphic
    1.96
    ographer
    1.95
    GRAPHY
    1.93
    ographers
    1.92
    ografía
    1.83
    ografi
    1.78
    ographical
    1.76
    Activations Density 0.026%

    No Known Activations