© 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. 4-CLT-HP
    7. 261
    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
    DockStyle
    -0.66
    astify
    -0.63
     chi̍t
    -0.59
    bootstrapcdn
    -0.58
    ArgumentParser
    -0.53
    ishna
    -0.52
    MessageTagHelper
    -0.52
    vernote
    -0.52
     насеље
    -0.51
    tvguidetime
    -0.48
    POSITIVE LOGITS
     ability
    0.68
     capacity
    0.60
    RegressionTest
    0.59
    :✨
    0.57
     possibility
    0.54
     future
    0.54
    رشف
    0.53
    MigrationBuilder
    0.53
     effectiveness
    0.53
     overall
    0.53
    Activations Density 0.004%

    No Known Activations