© 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. 3236
    Prev
    Next
    INDEX
    Explanations

    references to optical measurement techniques and related concepts

    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
     eye
    -1.28
     eyes
    -1.20
    eye
    -1.09
    Eye
    -1.08
     Eye
    -1.03
    eyes
    -1.00
     Eyes
    -0.99
     eyed
    -0.91
    eyed
    -0.91
    EYE
    -0.90
    POSITIVE LOGITS
     optical
    2.39
     Optical
    2.20
    Optical
    2.14
    optical
    2.14
     optically
    1.33
     опти
    1.22
     óptica
    1.05
     optique
    1.02
     Optics
    1.01
     optics
    0.95
    Activations Density 0.015%

    No Known Activations