© 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. 25274
    Prev
    Next
    INDEX
    Explanations

    the presence of specific gene expressions related to cancer research

    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
    HET
    -0.76
    ImageContext
    -0.74
    o
    -0.70
    єра
    -0.69
    OGND
    -0.69
     exemp
    -0.69
    unhofer
    -0.69
    parsedMessage
    -0.68
     Goy
    -0.68
     Fland
    -0.68
    POSITIVE LOGITS
    rH
    0.86
    s
    0.84
    H
    0.83
     H
    0.82
    dH
    0.77
     jPanel
    0.75
     municipales
    0.72
     vertes
    0.72
     auquel
    0.71
    attaque
    0.71
    Activations Density 0.076%

    No Known Activations