© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4911
    Prev
    Next
    INDEX
    Explanations

    logical connectors indicating sequences or relationships, often presented with intensifying or coordinating conjunctions

    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
     виправивши
    -1.05
     pauv
    -0.92
     plufieurs
    -0.89
     Echin
    -0.88
     ―――――
    -0.87
     Theſe
    -0.85
     Савезне
    -0.84
     ainfi
    -0.84
    NameInMap
    -0.83
    Gön
    -0.83
    POSITIVE LOGITS
     que
    2.25
     Que
    1.90
    Que
    1.83
     QUE
    1.69
    que
    1.62
    QUE
    1.17
     che
    1.09
     què
    0.87
     qué
    0.86
    Qué
    0.81
    Activations Density 0.018%

    No Known Activations