© 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. 0-CLT-HP
    7. 42654
    Prev
    Next
    INDEX
    Explanations

    his

    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
     his
    -1.84
    his
    -1.26
    His
    -1.16
     His
    -1.05
     their
    -1.02
     hänen
    -0.96
     seiner
    -0.96
    mybatisplus
    -0.95
     jego
    -0.94
     그의
    -0.94
    POSITIVE LOGITS
     own
    1.13
     current
    0.75
     favorite
    0.72
     usual
    0.71
     latest
    0.71
     entire
    0.70
     greatest
    0.67
     initial
    0.66
     main
    0.65
     favourite
    0.65
    Activations Density 0.113%

    No Known Activations