© 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. 5212
    Prev
    Next
    INDEX
    Explanations

    mentions of bodies of water, especially seas and oceans

    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
    tagHelperRunner
    -0.78
     Signalez
    -0.73
    boats
    -0.72
     للمعارف
    -0.72
     boats
    -0.69
    henswürdigkeiten
    -0.69
    EndGlobalSection
    -0.67
    Boat
    -0.65
    Tikang
    -0.65
    Boats
    -0.63
    POSITIVE LOGITS
     sea
    3.28
     Sea
    2.81
    Sea
    2.70
    sea
    2.64
     SEA
    2.17
    SEA
    1.95
     seas
    1.41
    海
    1.36
     море
    1.27
     Seas
    1.24
    Activations Density 0.017%

    No Known Activations