© 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. 7145
    Prev
    Next
    INDEX
    Explanations

    references to the mean or average value of a quantity

    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
     sy
    -0.67
    sy
    -0.58
    si
    -0.56
     Sy
    -0.55
    syn
    -0.53
    Sy
    -0.49
    sync
    -0.47
     «
    -0.46
    logi
    -0.46
    Si
    -0.45
    POSITIVE LOGITS
    ys
    2.25
    YS
    1.71
     esternos
    1.14
     ys
    1.13
    ysk
    1.03
    Autoritní
    0.97
    Ys
    0.95
    yska
    0.93
     YS
    0.91
    ysin
    0.86
    Activations Density 0.008%

    No Known Activations