© 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. 9567
    Prev
    Next
    INDEX
    Explanations

    biological terms and entities related to microbial and biochemical processes

    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
    MigrationBuilder
    -0.94
    AsUp
    -0.80
    UserScript
    -0.80
     okuyayım
    -0.77
    astéroïdes
    -0.75
    RenderAtEndOf
    -0.74
     OFDb
    -0.72
    UrlResolution
    -0.71
    saraba
    -0.69
    WSGI
    -0.68
    POSITIVE LOGITS
    OGND
    0.46
    GraphicsUnit
    0.46
    fromCharCode
    0.46
    ervare
    0.45
    jud
    0.45
     Màu
    0.45
    mapStateToProps
    0.45
    ViewImports
    0.43
    hoots
    0.41
    ở
    0.41
    Activations Density 0.048%

    No Known Activations