© 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. 4-CLT-HP
    7. 4717
    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
    ніципа
    -0.88
     '\\;'
    -0.80
    OGND
    -0.76
    NameInMap
    -0.69
    StoryboardSegue
    -0.66
     Paglinawan
    -0.66
     disambiguazione
    -0.65
     فريبيس
    -0.65
    EDEFAULT
    -0.65
    帖最后由
    -0.64
    POSITIVE LOGITS
     role
    0.71
     impact
    0.65
     effect
    0.62
     can
    0.56
     failure
    0.54
     influence
    0.52
     work
    0.50
     status
    0.48
    beforeEach
    0.48
     ability
    0.48
    Activations Density 0.012%

    No Known Activations