© 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. 5-CLT-HP
    7. 92193
    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
    StructEnd
    -0.78
    SBATCH
    -0.63
     تضيفلها
    -0.62
     RoutedEventArgs
    -0.60
     kaynağından
    -0.60
    RenderAtEndOf
    -0.57
    DBNull
    -0.56
     quelcon
    -0.55
    estacks
    -0.54
     nemici
    -0.53
    POSITIVE LOGITS
     lowly
    0.57
     stature
    0.57
     young
    0.57
     youth
    0.56
     small
    0.56
     []).
    0.55
     background
    0.53
     diminutive
    0.52
     age
    0.52
    verwijspagina
    0.51
    Activations Density 0.006%

    No Known Activations