© 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. 11732
    Prev
    Next
    INDEX
    Explanations

    emphasis on quotation marks or expressions of strong feelings

    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
    SQLException
    -0.75
     Unwin
    -0.74
    Sai
    -0.71
     Sai
    -0.69
     Ricci
    -0.69
     Grimal
    -0.68
     Franke
    -0.66
     recognise
    -0.65
     Griffiths
    -0.65
     Irwin
    -0.64
    POSITIVE LOGITS
    ”
    0.96
     Puch
    0.77
     nahilalakip
    0.76
    parsedMessage
    0.71
    GEBURTSDATUM
    0.66
     bodyParser
    0.65
     Boug
    0.65
     виправивши
    0.63
    WebElementEntity
    0.63
    Eksterne
    0.63
    Activations Density 0.001%

    No Known Activations