© 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. 861
    Prev
    Next
    INDEX
    Explanations

    the word "band" in the context of physics and semiconductors

    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
    rences
    -0.54
     Fisch
    -0.50
     Vern
    -0.49
     Salem
    -0.49
     Wassers
    -0.49
    Vern
    -0.48
    PSI
    -0.48
    ̷
    -0.48
     West
    -0.47
     Sud
    -0.47
    POSITIVE LOGITS
     band
    3.44
     bands
    3.44
    Band
    3.25
     BAND
    3.23
    band
    3.20
     Bands
    3.19
     Band
    3.17
    BAND
    3.13
    bands
    3.02
    Bands
    2.89
    Activations Density 0.147%

    No Known Activations