© 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. 6694
    Prev
    Next
    INDEX
    Explanations

    terms related to telecommunications technology

    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
    存于互联网档案馆
    -1.05
    agoza
    -0.90
    antart
    -0.85
     AssemblyCulture
    -0.81
     Armand
    -0.81
     Schwä
    -0.79
    RunWith
    -0.77
    ItemBackground
    -0.77
    Württemberg
    -0.76
     Corsica
    -0.76
    POSITIVE LOGITS
     Tele
    1.72
     tele
    1.66
     TELE
    1.61
    Tele
    1.56
    tele
    1.46
    TELE
    1.41
     Teles
    1.20
    Teles
    1.13
     teleport
    1.10
     Telegraph
    1.09
    Activations Density 0.014%

    No Known Activations