© 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. 95380
    Prev
    Next
    INDEX
    Explanations

    possessive 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
     Their
    -0.98
    DoubleQuotes
    -0.93
     Monfieur
    -0.89
     His
    -0.88
    Their
    -0.85
     Your
    -0.84
    His
    -0.81
    Your
    -0.79
     YOUR
    -0.79
     Jego
    -0.78
    POSITIVE LOGITS
     Own
    0.75
    föl
    0.66
     Best
    0.59
     Very
    0.57
    }")]
    0.57
     Favorite
    0.56
    selves
    0.56
     Most
    0.54
    own
    0.54
    __":
    0.52
    Activations Density 0.811%

    No Known Activations