© 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. 1029
    Prev
    Next
    INDEX
    Explanations

    words in a variety of specific categories including locations, punishments, vehicular brands, objects, coding terms

    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
     […]
    -1.13
     [...]
    -0.82
    [...]
    -0.71
     ...
    -0.68
    <eos>
    -0.67
    ↵
    -0.67
     
    -0.66
    […]
    -0.64
     …
    -0.62
    ↵↵↵
    -0.59
    POSITIVE LOGITS
    LookAnd
    1.38
    Personensuche
    1.36
    adaptiveStyles
    1.34
     typelib
    1.33
     autorytatywna
    1.32
     AssemblyCulture
    1.30
    GEBURTSDATUM
    1.27
     defaultstate
    1.24
    tagHelperRunner
    1.23
    InjectAttribute
    1.21
    Activations Density 1.302%

    No Known Activations