© 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. 43567
    Prev
    Next
    INDEX
    Explanations

    PET

    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
     PET
    -0.48
     Peterson
    -0.48
     Pet
    -0.42
     való
    -0.41
     Peters
    -0.41
    ©
    -0.40
     Camp
    -0.40
     S
    -0.40
     extra
    -0.39
    Copyright
    -0.39
    POSITIVE LOGITS
     myſelf
    1.20
     itſelf
    1.13
     Monfieur
    1.12
     Efq
    1.07
     iſt
    1.03
     Jefus
    1.03
     themſelves
    1.02
     himſelf
    1.00
     Diſ
    1.00
     Eſ
    1.00
    Activations Density 0.548%

    No Known Activations