© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 410
    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
    ar
    -0.56
    *);
    -0.55
    ages
    -0.54
     Namely
    -0.54
    ph
    -0.54
    Phan
    -0.53
    fjspx
    -0.53
    ager
    -0.53
    anaf
    -0.52
    ClientSize
    -0.52
    POSITIVE LOGITS
     '{@
    0.65
     CreateTagHelper
    0.63
     propOrder
    0.59
    <bos>
    0.56
     <=",
    0.55
    esterday
    0.54
     ciascuno
    0.52
    клопе
    0.52
    berdayakan
    0.51
     تانيه
    0.51
    Activations Density 0.042%

    No Known Activations