© 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. 4-CLT-HP
    7. 2772
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
    -0.95
    MigrationBuilder
    -0.89
    RenderAtEndOf
    -0.87
    SequentialGroup
    -0.85
     متعلقه
    -0.85
     AssemblyCulture
    -0.81
    tagHelperRunner
    -0.80
    writeFieldEnd
    -0.77
    SharedDtor
    -0.76
    DoubleQuotes
    -0.75
    POSITIVE LOGITS
     true
    0.69
     real
    0.63
     condition
    0.57
     background
    0.56
    w
    0.54
     precise
    0.48
     situation
    0.48
     exact
    0.47
     inten
    0.47
    true
    0.47
    Activations Density 0.003%

    No Known Activations