© 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. 3084
    Prev
    Next
    INDEX
    Explanations

    the word "wave" in the context of physics and quantum mechanics.

    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
    loem
    -0.70
     Tash
    -0.62
    ulario
    -0.60
    ktop
    -0.60
     protons
    -0.60
    crites
    -0.60
    piration
    -0.59
    omotor
    -0.59
    utuhkan
    -0.59
    anyaan
    -0.58
    POSITIVE LOGITS
     wave
    3.14
    wave
    2.89
     Wave
    2.86
    Wave
    2.72
     waves
    2.48
     WAVE
    2.48
    WAVE
    2.28
    waves
    2.25
     Waves
    2.14
    Waves
    1.95
    Activations Density 0.033%

    No Known Activations