© 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. 57
    Prev
    Next
    INDEX
    Explanations

    words related to various specific fields such as medical, technical/academic research, marketing, history, database architecture, community development, project management, and battery technology

    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
     enfans
    -1.15
     oreilles
    -1.13
     dieux
    -1.12
     varandra
    -1.10
     définiti
    -1.10
     quelcon
    -1.09
     larmes
    -1.09
     Juifs
    -1.06
     ainfi
    -1.04
     prisonniers
    -1.04
    POSITIVE LOGITS
    -
    1.10
     system
    1.04
     and
    1.02
     activity
    0.94
     process
    0.94
     status
    0.93
     data
    0.91
     information
    0.91
     systems
    0.90
     program
    0.89
    Activations Density 12.646%

    No Known Activations