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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 550
    Prev
    Next
    INDEX
    Explanations

    medical texts

    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
     оригіналу
    -0.54
    Rüyada
    -0.53
     &___
    -0.53
     ringer
    -0.52
    anek
    -0.50
     Donahue
    -0.50
    AMO
    -0.49
    #+#
    -0.49
    richTextPanel
    -0.48
    ]._
    -0.48
    POSITIVE LOGITS
    mybatisplus
    0.70
    writeFieldEnd
    0.61
     SwiftUI
    0.57
     vya
    0.55
    DispatchToProps
    0.54
     vectorielle
    0.51
    #
    0.50
     jorden
    0.50
    SPATH
    0.50
     thiệu
    0.49
    Activations Density 0.020%

    No Known Activations