© 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. 5-CLT-HP
    7. 93485
    Prev
    Next
    INDEX
    Explanations

    3

    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
     vœux
    -0.54
     eletrônico
    -0.53
     ControllerBase
    -0.53
    quelles
    -0.52
    xaml
    -0.52
    viedo
    -0.52
     réunis
    -0.51
     larmes
    -0.51
     jotka
    -0.50
     cuál
    -0.50
    POSITIVE LOGITS
    RegressionTest
    0.58
     issues
    0.55
     victims
    0.54
    Hochspringen
    0.54
    tvguidetime
    0.53
    DllImport
    0.52
    帖最后由
    0.52
     problems
    0.51
     products
    0.51
     users
    0.51
    Activations Density 0.001%

    No Known Activations