© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91212
    Prev
    Next
    INDEX
    Explanations

    "-ed" past participles

    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
     AssemblyProduct
    -0.90
    IntoConstraints
    -0.89
    SharedCtor
    -0.88
    styleType
    -0.87
    :✨
    -0.87
    quelize
    -0.84
     AssemblyVersion
    -0.77
     nahilalakip
    -0.77
    AsUp
    -0.77
    Diwedd
    -0.76
    POSITIVE LOGITS
     by
    0.67
     has
    0.66
     went
    0.62
     have
    0.60
     became
    0.51
     oleh
    0.51
     contains
    0.48
     must
    0.47
     may
    0.47
     awaits
    0.47
    Activations Density 0.015%

    No Known Activations