© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1193
    Prev
    Next
    INDEX
    Explanations

    references to Federal Rules and court decisions

    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.22.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.22.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
     religieuse
    -0.57
     Manuscripts
    -0.56
     Cytometry
    -0.56
    mặt
    -0.56
     IConfiguration
    -0.53
     figurative
    -0.53
     citation
    -0.51
     esterni
    -0.51
    Kaynakça
    -0.50
     intravenous
    -0.50
    POSITIVE LOGITS
     Assn
    0.67
     otomatig
    0.67
     Insp
    0.66
     الرياضيه
    0.66
     Univ
    0.66
    Univ
    0.66
    RenderAtEndOf
    0.64
     estekak
    0.62
     Gov
    0.62
     NSCoder
    0.61
    Activations Density 0.474%

    No Known Activations