© 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. 14839
    Prev
    Next
    INDEX
    Explanations

    specific medical or physiological terms related to health and clinical conditions

    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
    saraba
    -0.87
    iſh
    -0.78
    ghijklmnop
    -0.75
     houſe
    -0.75
    ſelves
    -0.74
    ſhip
    -0.74
     purpoſe
    -0.73
    fible
    -0.71
    neſs
    -0.70
    leſs
    -0.70
    POSITIVE LOGITS
     betweenstory
    0.68
    SpringBootTest
    0.67
    OGND
    0.65
     ProtoMessage
    0.63
    HasAnnotation
    0.61
    CDCl
    0.57
    styleable
    0.54
     mxArray
    0.54
    MigrationBuilder
    0.53
    riwal
    0.52
    Activations Density 0.481%

    No Known Activations