© 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. 1-CLT-HP
    7. 11435
    Prev
    Next
    INDEX
    Explanations

    associated

    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
     religieuses
    -0.59
     elevados
    -0.52
     aliran
    -0.52
     élevés
    -0.51
     élevées
    -0.50
     äldre
    -0.49
     órdenes
    -0.48
     kemasan
    -0.48
     militaires
    -0.47
     supérieurs
    -0.47
    POSITIVE LOGITS
     feathers
    0.67
    RegressionTest
    0.66
     birds
    0.66
    windowFixed
    0.66
     weeds
    0.66
     jadx
    0.65
     weevil
    0.65
    ConstraintMaker
    0.64
    AccessorTable
    0.64
     beetles
    0.63
    Activations Density 0.017%

    No Known Activations