© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1813
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to manufacturing or industrial processes, sometimes with the addition of financial or international topics.

    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
    avigation
    -0.58
    Datuak
    -0.57
     kasarigan
    -0.56
    adeloupe
    -0.51
    Airbnb
    -0.51
    chenkt
    -0.50
    WriteBarrier
    -0.49
     FLAC
    -0.49
     getopt
    -0.47
    tvguidetime
    -0.47
    POSITIVE LOGITS
     manufacturing
    1.98
     manufacture
    1.83
     production
    1.73
    manufacturing
    1.66
     Manufacturing
    1.62
    Manufacturing
    1.49
     factory
    1.48
     Production
    1.46
     Manufacture
    1.46
    production
    1.44
    Activations Density 2.169%

    No Known Activations