© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 894
    Prev
    Next
    INDEX
    Explanations

    references to websites and official organizations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.56
     الدولى
    -0.52
    Geplaatst
    -0.52
    GEBURTS
    -0.49
     BoxDecoration
    -0.49
    PLIED
    -0.47
    gbaar
    -0.47
    _));
    -0.47
    
    -0.47
     schreef
    -0.46
    POSITIVE LOGITS
     website
    2.34
     site
    2.17
    website
    1.90
     Website
    1.80
     websites
    1.80
     web
    1.70
     webpage
    1.66
     sites
    1.63
    Website
    1.63
     WEBSITE
    1.59
    Activations Density 1.008%

    No Known Activations