© 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. 6-RES-MATRYOSHKA-DC
    7. 441
    Prev
    Next
    INDEX
    Explanations

    words that are preceded by prepositions or that relate to legal/financial documents

    oai_token-act-pair · gemini-2.0-flash
    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
    gameserver
    -0.59
    bitField
    -0.56
    empre
    -0.54
    ۡ
    -0.51
    inghouse
    -0.51
    Vader
    -0.49
     everything
    -0.48
     something
    -0.48
    rens
    -0.48
    Дру
    -0.48
    POSITIVE LOGITS
     fellow
    0.84
     pihak
    0.78
     kalangan
    0.75
    raszamy
    0.74
     auprès
    0.73
     people
    0.72
    raszam
    0.72
     whome
    0.71
     BorderRadius
    0.70
    sendTo
    0.68
    Activations Density 4.027%

    No Known Activations