© 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. 8592
    Prev
    Next
    INDEX
    Explanations

    references to specific pathways or factors related to epithelial-mesenchymal transition (EMT) in biological contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -1.01
    Tikang
    -0.99
    SourceChecksum
    -0.96
    Hauptartikel
    -0.95
     CreateTagHelper
    -0.95
     estekak
    -0.88
    __':
    -0.85
    parsedMessage
    -0.84
     ProtoMessage
    -0.84
     дописавши
    -0.83
    POSITIVE LOGITS
     Wnt
    1.70
    gly
    0.64
    gle
    0.62
     Duncan
    0.60
    xon
    0.59
    x
    0.59
    cy
    0.59
    Pam
    0.58
    pen
    0.58
     جم
    0.58
    Activations Density 0.000%

    No Known Activations