© 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. 3970
    Prev
    Next
    INDEX
    Explanations

    numerical expressions related to scientific notation or specific energy values

    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
    »։
    -0.66
     ModelExpression
    -0.61
    Demikian
    -0.60
    Conclusie
    -0.57
     independientes
    -0.57
     "}";
    -0.57
    🏻
    -0.56
     Bookstore
    -0.56
     unabhäng
    -0.56
     ivelany
    -0.56
    POSITIVE LOGITS
    $^{-
    3.27
    $^
    2.34
    $^{
    1.58
    $_{
    1.35
    $_
    1.19
    $^{\
    1.09
    $^\
    0.96
    <sup>
    0.84
    <sub>
    0.74
     $^{\
    0.71
    Activations Density 0.002%

    No Known Activations