© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1768
    Prev
    Next
    INDEX
    Explanations

    diure

    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
    ers
    -1.10
    ERS
    -0.96
    ert
    -0.93
    erd
    -0.90
    ering
    -0.88
    ERING
    -0.68
    ered
    -0.66
    erts
    -0.65
    ERT
    -0.65
    erde
    -0.55
    POSITIVE LOGITS
     дописавши
    1.05
     Jefus
    0.99
    rungsseite
    0.98
    UnknownFieldSet
    0.96
     propOrder
    0.93
    Sucesor
    0.91
     MainAxisSize
    0.90
     becauſe
    0.89
     whoſe
    0.88
     himſelf
    0.86
    Activations Density 0.117%

    No Known Activations