© 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. 3200
    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
    CodedInputStream
    -0.85
    changers
    -0.74
    FieldBuilder
    -0.72
    RegistryLite
    -0.71
     Changes
    -0.70
     changed
    -0.69
     changes
    -0.69
     changer
    -0.68
     verändert
    -0.68
    rungsseite
    -0.67
    POSITIVE LOGITS
     tune
    0.57
     mind
    0.57
     modes
    0.54
     approach
    0.53
     point
    0.53
    RectangleBorder
    0.52
     mode
    0.52
     whole
    0.50
     approaches
    0.50
     entire
    0.48
    Activations Density 0.005%

    No Known Activations