© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10745
    Prev
    Next
    INDEX
    Explanations

    ors

    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
    w
    -0.51
    ors
    -0.50
     A
    -0.49
    en
    -0.47
    EN
    -0.46
     U
    -0.45
    c
    -0.43
    v
    -0.43
    op
    -0.42
    En
    -0.42
    POSITIVE LOGITS
    出版年
    1.20
     myſelf
    1.12
    AndEndTag
    1.11
     Monfieur
    1.09
     AssemblyCompany
    1.09
     pleaſure
    1.08
    LabelTagHelper
    1.08
     AssemblyCulture
    1.07
     MainAxisSize
    1.07
     للمعارف
    1.06
    Activations Density 0.071%

    No Known Activations