© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97139
    Prev
    Next
    INDEX
    Explanations

    reflexive 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
     themselves
    -2.45
    themselves
    -1.87
     ourselves
    -1.80
     yourselves
    -1.70
     yourself
    -1.48
     himself
    -1.45
     itself
    -1.40
     herself
    -1.39
     themſelves
    -1.28
     oneself
    -1.26
    POSITIVE LOGITS
     OMITBAD
    0.66
    getWriter
    0.64
    Einzelnachweise
    0.62
     AppCompat
    0.62
    DoubleQuotes
    0.62
    #
    
    0.60
    SwitchCompat
    0.60
    existsSync
    0.59
    phazard
    0.59
     sons
    0.58
    Activations Density 0.007%

    No Known Activations