© 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. 11248
    Prev
    Next
    INDEX
    Explanations

    legal and medical terminology related to claims and diagnoses

    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
    исленность
    -0.70
    ContentAsync
    -0.61
    UnknownFields
    -0.59
    tonsoft
    -0.57
    /*
    -0.56
    accro
    -0.55
    ukses
    -0.54
     réservation
    -0.52
    StructEnd
    -0.52
    ContentAlignment
    -0.51
    POSITIVE LOGITS
     recovery
    0.93
     Recovery
    0.83
    recovery
    0.81
     recover
    0.78
     recovering
    0.77
    Recovery
    0.77
     recovered
    0.75
    recover
    0.74
    recovered
    0.73
     Recover
    0.71
    Activations Density 0.834%

    No Known Activations