© 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. 23124
    Prev
    Next
    INDEX
    Explanations

    terms related to numerical values or data formats

    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
     NSCoder
    -0.79
    fillType
    -0.75
    TableBody
    -0.71
     protoimpl
    -0.67
     unknownFields
    -0.67
    arote
    -0.66
    
    -0.65
    gway
    -0.65
    IUrlHelper
    -0.65
    CodeAttribute
    -0.63
    POSITIVE LOGITS
    ‚¬
    1.11
     municipale
    0.59
    extrême
    0.59
     oreilles
    0.58
     circulaire
    0.54
     plastiques
    0.53
     linguistique
    0.53
     présidenti
    0.53
    publique
    0.52
     élus
    0.52
    Activations Density 0.004%

    No Known Activations