© 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. 10545
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions related to heart health and metabolism

    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
     nakalista
    -0.99
     autorytatywna
    -0.98
    SourceChecksum
    -0.97
    IUrlHelper
    -0.95
    Datuak
    -0.92
    principalTable
    -0.82
    LookAnd
    -0.81
    )}</
    -0.80
    MigrationBuilder
    -0.78
    دانشنامهٔ
    -0.76
    POSITIVE LOGITS
    書房
    0.49
    tième
    0.46
     third
    0.45
     ci
    0.44
     ihop
    0.43
     i
    0.43
    OptionsMenu
    0.43
    unately
    0.42
     Lower
    0.42
    Third
    0.42
    Activations Density 0.012%

    No Known Activations