© 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. 18-RES-MATRYOSHKA-DC
    7. 1537
    Prev
    Next
    INDEX
    Explanations

    capital letters followed by periods, common in citations and abbreviations

    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.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     disponibilités
    -0.81
    +#+#
    -0.76
    ური
    -0.70
    Identyfik
    -0.68
    uliert
    -0.65
    комму
    -0.65
    Hozzáférés
    -0.63
    MIDDLEWARE
    -0.62
     useContext
    -0.59
     AssemblyTitle
    -0.59
    POSITIVE LOGITS
     Rask
    0.75
     ràng
    0.73
     Ril
    0.70
     useRouter
    0.68
     Rous
    0.66
     rê
    0.66
     Rumble
    0.65
    R
    0.64
    ArrowToggle
    0.63
     RDC
    0.62
    Activations Density 1.981%

    No Known Activations