© 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. 2-RES-MATRYOSHKA-DC
    7. 6925
    Prev
    Next
    INDEX
    Explanations

    references to the word "throughout," indicating that it detects mentions of a recurrent or continuous process or period

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LikeLike
    -0.79
    cun
    -0.58
    "];
    -0.57
    airs
    -0.56
    awaiter
    -0.55
     Cross
    -0.54
    ]))
    -0.54
    AllAfrica
    -0.54
    nog
    -0.53
    a
    -0.53
    POSITIVE LOGITS
    throughout
    2.61
     throughout
    2.50
     Throughout
    2.20
    Throughout
    2.16
     THRO
    1.38
    HOUT
    1.23
     sepanjang
    1.01
     partout
    1.00
    everywhere
    1.00
     ovunque
    0.99
    Activations Density 0.012%

    No Known Activations