© 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. 25400
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and trends in scientific data

    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
     للمعارف
    -1.02
     дописавши
    -0.90
     مرئيه
    -0.79
    DeleteBehavior
    -0.77
    ANTLR
    -0.77
     defaultstate
    -0.76
    RTLD
    -0.76
     Chwiliwch
    -0.75
     CreateTagHelper
    -0.75
     سكانية
    -0.73
    POSITIVE LOGITS
    Select
    0.43
     selects
    0.40
    DockStyle
    0.39
    нь
    0.38
    Bronnen
    0.38
     provincias
    0.36
     iyo
    0.36
    MAND
    0.36
    [
    0.36
    واد
    0.36
    Activations Density 0.061%

    No Known Activations