© 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. 43937
    Prev
    Next
    INDEX
    Explanations

    Open curly brace

    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
     JpaRepository
    -0.89
     <=",
    -0.84
    ROIT
    -0.82
    OrNil
    -0.79
    OGND
    -0.74
    theless
    -0.74
     lenker
    -0.73
    istoitu
    -0.71
    APORE
    -0.70
     itſelf
    -0.70
    POSITIVE LOGITS
     im
    0.54
     AssemblyCulture
    0.51
     import
    0.50
     memb
    0.49
     IM
    0.49
    diac
    0.48
     McBride
    0.47
     bien
    0.46
    writeTo
    0.46
     pas
    0.46
    Activations Density 1.855%

    No Known Activations