© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13545
    Prev
    Next
    INDEX
    Explanations

    references to medical imaging involving the lungs or alveolar 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
     ligiloj
    -0.56
    bolista
    -0.54
    Clik
    -0.51
     Chwiliwch
    -0.50
    NegativeButton
    -0.50
     maz
    -0.50
    chyma
    -0.50
     Vul
    -0.48
    chach
    -0.48
     throw
    -0.47
    POSITIVE LOGITS
    illary
    4.22
    illaries
    1.24
     capillary
    0.88
    RegressionTest
    0.71
    iliary
    0.69
     дописавши
    0.63
    ModelSerializer
    0.62
     propOrder
    0.61
    illar
    0.60
     capillaries
    0.60
    Activations Density 0.000%

    No Known Activations