© 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. 7250
    Prev
    Next
    INDEX
    Explanations

    references to quantum operators and related mathematical structures

    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
    tilde
    -1.93
    widetilde
    -0.77
     lexer
    -0.63
     gắng
    -0.60
    simpleType
    -0.59
    ̃
    -0.58
    ittaa
    -0.57
    tiller
    -0.57
    yargs
    -0.56
     mergeFrom
    -0.55
    POSITIVE LOGITS
    hat
    1.49
     hat
    1.23
     Hat
    1.20
    HAT
    1.19
     HAT
    1.16
    Hat
    1.13
    boldsymbol
    1.01
     hats
    1.01
    hatt
    0.93
    hats
    0.89
    Activations Density 0.032%

    No Known Activations