© 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. 9103
    Prev
    Next
    INDEX
    Explanations

    names and identifiers related to pharmaceutical or medical entities

    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
    amaño
    -0.44
    regular
    -0.41
     loob
    -0.40
     regular
    -0.39
     master
    -0.39
     converted
    -0.39
     conversion
    -0.38
     fidanz
    -0.38
     Council
    -0.37
     fréquent
    -0.37
    POSITIVE LOGITS
    UnusedPrivate
    0.89
    Geplaatst
    0.79
    DoubleQuotes
    0.75
    Datuak
    0.74
     lenker
    0.73
    enumi
    0.72
     الحره
    0.70
    lgari
    0.70
    ########.
    0.70
    expandindo
    0.70
    Activations Density 0.023%

    No Known Activations