© 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. 12-RES-MATRYOSHKA-DC
    7. 2460
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to processes involving authority and regulation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     InputDecoration
    -0.83
    verwijspagina
    -0.70
    AntiForgeryToken
    -0.56
     الرياضيه
    -0.56
     correctes
    -0.53
    Демографія
    -0.53
    ępnie
    -0.48
    üm
    -0.47
    至今
    -0.47
    creativecommons
    -0.47
    POSITIVE LOGITS
     impending
    1.01
     upcoming
    0.99
     imminent
    0.93
    upcoming
    0.93
     Upcoming
    0.90
     forthcoming
    0.88
     planned
    0.86
     future
    0.86
     futuras
    0.84
     Gonna
    0.81
    Activations Density 0.420%

    No Known Activations