© 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. 1-RES-MATRYOSHKA-DC
    7. 864
    Prev
    Next
    INDEX
    Explanations

    references to photoelectric phenomena or images related to laser or electron-beam 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
    イメージ
    -0.68
     imaging
    -0.64
     Imaging
    -0.62
     image
    -0.60
    ContentAsync
    -0.57
     كومونز
    -0.57
     eingeb
    -0.57
    rungen
    -0.55
     Image
    -0.55
     obraz
    -0.55
    POSITIVE LOGITS
     photo
    4.03
     Photo
    3.73
    photo
    3.66
    Photo
    3.59
     PHOTO
    3.27
    PHOTO
    2.97
     foto
    2.91
     photos
    2.81
     Photos
    2.64
    Photos
    2.61
    Activations Density 0.047%

    No Known Activations