© 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. 20-CLT-HP
    7. 76361
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act-logits · 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
     that
    -1.02
     שוליים
    -0.61
     CreateTagHelper
    -0.60
    UnusedPrivate
    -0.54
     AssemblyCulture
    -0.52
    ">)</
    -0.51
     defaultstate
    -0.50
    oldt
    -0.48
    BeginContext
    -0.48
    })$}
    -0.47
    POSITIVE LOGITS
    they
    0.86
    who
    0.73
    THEY
    0.68
    quels
    0.67
    quien
    0.66
     οποίο
    0.63
    them
    0.63
    which
    0.63
    there
    0.61
    Mereka
    0.61
    Activations Density 0.000%

    No Known Activations