© 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. 157
    Prev
    Next
    INDEX
    Explanations

    the

    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
     שוליים
    -0.77
    .*")]
    -0.77
    IsContent
    -0.75
    UnitTesting
    -0.69
    makeConstraints
    -0.67
     Roskov
    -0.67
    原始内容存档于
    -0.66
    TagMode
    -0.66
     defaultstate
    -0.66
     otomatig
    -0.65
    POSITIVE LOGITS
     birth
    0.56
     arrival
    0.54
     anniversary
    0.51
     conclusion
    0.48
     nacimiento
    0.48
     commencement
    0.47
    
    0.46
     annual
    0.46
     start
    0.45
    abb
    0.45
    Activations Density 0.001%

    No Known Activations