© 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. 22-RES-MATRYOSHKA-DC
    7. 3115
    Prev
    Next
    INDEX
    Explanations

    research papers or statistical analysis.

    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/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     average
    -0.56
    SqlClient
    -0.52
    average
    -0.48
     jó
    -0.45
     peor
    -0.44
    уд
    -0.44
    Литература
    -0.43
    averaged
    -0.43
     đỏ
    -0.41
    tructive
    -0.41
    POSITIVE LOGITS
    出版年
    0.95
     <<<<<<<<<<<<<<
    0.90
    ंदीखरीदारी
    0.84
    ConstraintMaker
    0.76
    AccessorTable
    0.72
     unless
    0.70
     Paglinawan
    0.69
    GEBURTSDATUM
    0.68
    reportWebVitals
    0.67
    BeginContext
    0.67
    Activations Density 0.135%

    No Known Activations