© 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. 43728
    Prev
    Next
    INDEX
    Explanations

    disability/medical

    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
     elevator
    -0.88
     Efq
    -0.86
     Monfieur
    -0.81
     AssemblyCompany
    -0.80
     Anſ
    -0.78
     elevators
    -0.77
     Cabe
    -0.77
     leaſt
    -0.75
     myſelf
    -0.74
     poffe
    -0.72
    POSITIVE LOGITS
     betweenstory
    0.56
     consultato
    0.52
    цездатний
    0.52
    IContainer
    0.51
     оригіналу
    0.47
    itza
    0.46
    versch
    0.46
    igera
    0.43
     calendriers
    0.43
     berk
    0.43
    Activations Density 0.126%

    No Known Activations