© 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. 0-RES-MATRYOSHKA-DC
    7. 11264
    Prev
    Next
    INDEX
    Explanations

    references to the term "furthermore" or "moreover," indicating it detects the presence of these discourse markers

    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
    veland
    -0.65
     >=",
    -0.57
     EClass
    -0.52
    NOPQRST
    -0.52
    ⓧ
    -0.52
    EndGlobal
    -0.51
    lné
    -0.49
     slee
    -0.48
    (">
    -0.48
     loo
    -0.48
    POSITIVE LOGITS
     moreover
    2.53
     furthermore
    2.39
     additionally
    1.03
     dessutom
    0.97
     inoltre
    0.92
     navíc
    0.90
     conversely
    0.81
     ayrıca
    0.81
     likewise
    0.74
     zudem
    0.72
    Activations Density 0.001%

    No Known Activations