© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24405
    Prev
    Next
    INDEX
    Explanations

    terms related to "socket" in a technical context

    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
    Negative Logits
    Bretagne
    -0.78
    boxylic
    -0.73
     przet
    -0.73
    eme
    -0.67
    urgical
    -0.65
    annica
    -0.65
    emia
    -0.64
     Brum
    -0.64
    ^[
    -0.63
    ETT
    -0.63
    POSITIVE LOGITS
     sockaddr
    1.52
     sock
    1.51
     Sock
    1.50
    sock
    1.45
     socks
    1.31
    Sock
    1.30
     SOCK
    1.18
     Socks
    1.16
    SOCK
    1.13
    Socks
    1.11
    Activations Density 0.002%

    No Known Activations