© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3472
    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
    SharedCtor
    -0.64
    aság
    -0.54
    ніципалі
    -0.50
    StoryboardSegue
    -0.49
     bezeichneter
    -0.46
    AHN
    -0.46
    سطس
    -0.46
    RTN
    -0.45
     oublié
    -0.45
    roveň
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.67
    yelidikan
    0.61
     objection
    0.60
     pledge
    0.56
    useState
    0.53
     decade
    0.52
     bedrag
    0.51
    Moda
    0.50
    damente
    0.49
     confetti
    0.49
    Activations Density 0.002%

    No Known Activations