© 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. 15073
    Prev
    Next
    INDEX
    Explanations

    terms related to automated document processing and claims

    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
     nahilalakip
    -0.73
     سكانية
    -0.64
    __*/
    -0.56
    はじめに
    -0.56
    الحياه
    -0.53
    farin
    -0.53
    Manbalar
    -0.52
     ân
    -0.52
    EndProject
    -0.51
    AndroidJUnit
    -0.51
    POSITIVE LOGITS
     OBITUARY
    0.57
    jface
    0.56
     produisons
    0.54
    \|^{
    0.52
     otomatig
    0.52
     EClass
    0.52
    ScopeManager
    0.52
    Kommentare
    0.50
    xsd
    0.50
    annelse
    0.50
    Activations Density 0.050%

    No Known Activations