© 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. 17325
    Prev
    Next
    INDEX
    Explanations

    content related to financial issues and moral debates

    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
    IContainer
    -0.54
     caused
    -0.46
     Accountants
    -0.45
     unrelenting
    -0.45
    تفصیلات
    -0.45
     claiming
    -0.45
     resourceCulture
    -0.45
     estekak
    -0.44
    escens
    -0.44
    ρης
    -0.43
    POSITIVE LOGITS
    ArgsConstructor
    0.72
    ExtendWith
    0.70
    ElementException
    0.62
     itſelf
    0.60
    hdashline
    0.60
     للاسماء
    0.57
    vikle
    0.57
    IntoConstraints
    0.56
    حياتها
    0.56
    ništ
    0.56
    Activations Density 0.173%

    No Known Activations