© 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. 40168
    Prev
    Next
    INDEX
    Explanations

    abbreviations and communication

    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
    AndEndTag
    -1.42
    AnchorStyles
    -1.39
    EndInit
    -1.27
    enumi
    -1.23
     متعلقه
    -1.21
    PerformLayout
    -1.20
     '\\;'
    -1.19
    AddTagHelper
    -1.16
    BeginInit
    -1.15
    IsContent
    -1.14
    POSITIVE LOGITS
     the
    0.74
     is
    0.62
     to
    0.57
     was
    0.57
     a
    0.56
     not
    0.56
     it
    0.54
     for
    0.54
     as
    0.54
    ,
    0.52
    Activations Density 0.141%

    No Known Activations