© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15107
    Prev
    Next
    INDEX
    Explanations

    medical procedures and airways

    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
    bre
    -0.85
    BRE
    -0.72
     BRE
    -0.62
    bres
    -0.61
    HttpPost
    -0.60
    jspb
    -0.59
    بوابة
    -0.58
    izos
    -0.57
    ContentAsync
    -0.57
    ANTLR
    -0.56
    POSITIVE LOGITS
     Hygiene
    0.49
     Normdatei
    0.48
    creva
    0.47
     Tissue
    0.47
     Jolie
    0.46
    premise
    0.46
    NewUrlParser
    0.45
    Vidite
    0.45
     hygiene
    0.44
     Jovi
    0.44
    Activations Density 0.038%

    No Known Activations