© 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. 3-RES-MATRYOSHKA-DC
    7. 1928
    Prev
    Next
    INDEX
    Explanations

    the word "down" and its inflections

    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
     up
    -0.79
    BeforeClass
    -0.73
     Magi
    -0.71
    Up
    -0.70
    up
    -0.69
     Up
    -0.69
    FormTagHelper
    -0.64
    OnTop
    -0.63
     majeur
    -0.62
     dorsal
    -0.61
    POSITIVE LOGITS
     down
    2.52
     Down
    2.30
    Down
    2.25
    down
    2.20
     DOWN
    2.20
    DOWN
    2.05
    downs
    2.02
     downs
    1.89
    Downs
    1.84
     Downs
    1.74
    Activations Density 0.528%

    No Known Activations