© 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. 1042
    Prev
    Next
    INDEX
    Explanations

    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
     InputDecoration
    -0.62
    getDeclared
    -0.55
     disambiguazione
    -0.53
    IMPORTED
    -0.52
    GEBURTS
    -0.51
     dumped
    -0.50
    PRNewswire
    -0.50
    ourite
    -0.49
    Personensuche
    -0.48
    alló
    -0.48
    POSITIVE LOGITS
     deal
    0.63
     kasarigan
    0.62
    RenderAtEndOf
    0.55
     participate
    0.53
     wish
    0.51
     first
    0.51
     experiment
    0.50
    :^(
    0.50
    '
    0.49
    이션
    0.49
    Activations Density 0.005%

    No Known Activations