© 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. 24-RES-MATRYOSHKA-DC
    7. 1329
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and concepts related to the description and nature of diseases or illnesses.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
     propOrder
    -0.71
     estekak
    -0.68
     kasarigan
    -0.58
     utafitiHapana
    -0.55
    ()));
    -0.54
    QMetaType
    -0.53
     препратки
    -0.53
    upy
    -0.51
    enterOuterAlt
    -0.50
     biceps
    -0.50
    POSITIVE LOGITS
     diseases
    1.13
     disease
    1.07
     condition
    1.06
     disorder
    1.02
     disorders
    1.02
     Condition
    0.91
    condition
    0.91
     illness
    0.90
     Diseases
    0.89
     illnesses
    0.89
    Activations Density 0.665%

    No Known Activations