© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 12735
    Prev
    Next
    INDEX
    Explanations

    terms related to immunosuppression and its effects

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     Dage
    -0.59
     Hallen
    -0.59
     oce
    -0.56
    หวัด
    -0.52
     felb
    -0.52
    atur
    -0.50
     clen
    -0.50
     Oce
    -0.50
    UnitTesting
    -0.50
    ژه
    -0.49
    POSITIVE LOGITS
     immunosupp
    1.46
    limus
    1.02
     שוליים
    0.77
    oporosis
    0.72
    moons
    0.66
    StreetMap
    0.65
    unschweig
    0.65
     firebaseConfig
    0.64
     StatefulWidget
    0.62
    "}")
    0.62
    Activations Density 0.009%

    No Known Activations