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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14013
    Prev
    Next
    INDEX
    Explanations

    references to the Taiping Dynasty or its monarchs

    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
     myſelf
    -0.77
    CloseOperation
    -0.74
    seamnă
    -0.70
    newswire
    -0.68
     CHtml
    -0.68
     iſt
    -0.68
     whoſe
    -0.68
    !*\
    -0.67
    horabuena
    -0.67
     fathoms
    -0.66
    POSITIVE LOGITS
     Ta
    1.78
     taper
    1.56
    Ta
    1.55
     tapered
    1.23
     tapering
    1.18
     Taq
    0.86
     Taub
    0.56
     Te
    0.53
     TAP
    0.51
    Te
    0.50
    Activations Density 0.004%

    No Known Activations