© 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. 18883
    Prev
    Next
    INDEX
    Explanations

    references to a specific stem cell type and related terms

    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
    QMetaType
    -0.86
    WebElementEntity
    -0.85
     Haarlem
    -0.85
    Lähteet
    -0.84
     Houſe
    -0.82
    Cyfeiriadau
    -0.81
     Nt
    -0.81
    TestFixture
    -0.77
     gepubliceerd
    -0.77
    atement
    -0.76
    POSITIVE LOGITS
    MSC
    1.70
     MSC
    1.61
     “
    0.66
    msc
    0.66
     Schles
    0.65
     vů
    0.65
    enchymal
    0.61
    RegistryLite
    0.61
    <strong>
    0.60
    ’
    0.59
    Activations Density 0.001%

    No Known Activations