© 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. 6-RES-MATRYOSHKA-DC
    7. 1452
    Prev
    Next
    INDEX
    Explanations

    contextual clues indicative of comparison

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    addPreferredGap
    -0.68
    adaptiveStyles
    -0.57
     مشين
    -0.57
    MLLoader
    -0.54
     Wikimédia
    -0.54
    
    -0.54
    Obrázky
    -0.54
     Chwiliwch
    -0.52
    <?>>
    -0.50
     Gode
    -0.49
    POSITIVE LOGITS
     oprot
    0.63
    paravant
    0.61
     ones
    0.59
     Diretto
    0.58
    AndEndTag
    0.58
    jiri
    0.57
     usual
    0.56
     davor
    0.54
     ordinaires
    0.53
     tradisional
    0.53
    Activations Density 2.986%

    No Known Activations