© 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. 0-CLT-HP
    7. 42117
    Prev
    Next
    INDEX
    Explanations

    shunt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.90
    istocene
    -0.80
    CopyWith
    -0.74
     FetchType
    -0.71
    testens
    -0.69
     BrowserRouter
    -0.69
    uxxxx
    -0.69
    WEBPACK
    -0.68
     déchir
    -0.68
     ReactDOM
    -0.66
    POSITIVE LOGITS
    ware
    0.68
    board
    0.66
    house
    0.64
    book
    0.61
    tacular
    0.60
    plate
    0.59
    box
    0.59
    hold
    0.57
    works
    0.57
    work
    0.56
    Activations Density 0.387%

    No Known Activations