© 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. 25590
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and expressions involving limits and integrals to describe functions and their properties

    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
     تعدى
    -0.60
    leck
    -0.60
     FetchType
    -0.54
    WebElementEntity
    -0.52
     Gek
    -0.51
     Kell
    -0.51
    seid
    -0.51
    
    -0.50
     newOwner
    -0.48
     snippetHide
    -0.48
    POSITIVE LOGITS
    SharedCtor
    0.82
    RegressionTest
    0.70
     propOrder
    0.70
     ProtoMessage
    0.60
     Numerade
    0.60
     lenker
    0.59
    DockStyle
    0.59
     Justo
    0.59
    AccessorTable
    0.55
    seamnă
    0.54
    Activations Density 0.014%

    No Known Activations