© 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. 17086
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax, particularly the definition of content in styles or functions

    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
     يتيمه
    -0.70
    ChildScrollView
    -0.68
    mergeFrom
    -0.63
     autorytatywna
    -0.60
     lenker
    -0.60
     TestBed
    -0.59
    Portail
    -0.58
    barui
    -0.57
    AndEndTag
    -0.57
     disambiguazione
    -0.56
    POSITIVE LOGITS
    وفة
    0.51
     profits
    0.51
    InputTagHelper
    0.51
     drivers
    0.50
     Preguntas
    0.50
    PRESS
    0.49
     grits
    0.48
     productName
    0.48
     MatDialog
    0.48
    culin
    0.48
    Activations Density 0.001%

    No Known Activations