© 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. 5-CLT-HP
    7. 96502
    Prev
    Next
    INDEX
    Explanations

    Possessive pronouns, personal stories

    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
    principalTable
    -0.78
     فريبيس
    -0.76
    WriteBarrier
    -0.71
    UIControlState
    -0.64
    GEBURTSDATUM
    -0.61
     BoxFit
    -0.61
    μως
    -0.61
    
    -0.60
    出版年
    -0.59
    rawDesc
    -0.59
    POSITIVE LOGITS
     otherwise
    0.69
     usually
    0.57
     normally
    0.57
     carefully
    0.52
     sonst
    0.52
    otherwise
    0.51
     previously
    0.50
     easy
    0.49
     once
    0.49
     typically
    0.49
    Activations Density 0.003%

    No Known Activations