© 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. 6325
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical studies and 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
    Not in Any Lists

    No Comments

    Negative Logits
    ecore
    -0.53
     Agamemnon
    -0.50
     positively
    -0.50
    donna
    -0.48
    shutil
    -0.48
     WMA
    -0.47
     uſed
    -0.47
     orientale
    -0.46
    گاب
    -0.46
     Sauvignon
    -0.46
    POSITIVE LOGITS
     pinulongan
    0.83
     Савезне
    0.79
    MigrationBuilder
    0.65
    ########.
    0.65
     ComVisible
    0.59
    MessageTagHelper
    0.58
     transfieras
    0.58
    رشف
    0.57
    alya
    0.56
    исленность
    0.56
    Activations Density 0.247%

    No Known Activations