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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16427
    Prev
    Next
    INDEX
    Explanations

    references to social dynamics and actions involving people

    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
    φορά
    -0.54
     l
    -0.48
     an
    -0.44
     a
    -0.44
    fikasi
    -0.44
     dimiliki
    -0.43
    l
    -0.43
    ja
    -0.42
    でもある
    -0.41
     Ja
    -0.41
    POSITIVE LOGITS
     Efq
    0.93
    出版年
    0.89
    jsonwebtoken
    0.88
     lenker
    0.85
     EconPapers
    0.84
    UnusedPrivate
    0.82
    routeProvider
    0.82
    #+#
    0.78
    UserScript
    0.78
    таратура
    0.78
    Activations Density 0.162%

    No Known Activations