© 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. 76992
    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
    TintMode
    -0.56
    SuspendLayout
    -0.54
    HomeAsUpEnabled
    -0.53
     disambiguazione
    -0.50
    CppMethod
    -0.47
    hasMoreElements
    -0.46
    kaŭ
    -0.44
    clinic
    -0.43
    AndEndTag
    -0.42
    tudo
    -0.42
    POSITIVE LOGITS
     him
    1.65
     them
    1.53
     you
    1.42
     us
    1.28
    them
    1.14
     lui
    1.06
    him
    0.97
     THEM
    0.91
     вам
    0.90
     Them
    0.85
    Activations Density 0.010%

    No Known Activations