© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1071
    Prev
    Next
    INDEX
    Explanations

    and, comma

    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
     betweenstory
    -0.96
     CreateTagHelper
    -0.78
    AddHtmlAttribute
    -0.71
    unknownFields
    -0.68
    parsedMessage
    -0.66
    AndEndTag
    -0.66
     protoimpl
    -0.63
     autorytatywna
    -0.62
     otomatig
    -0.61
    hoeddwyd
    -0.60
    POSITIVE LOGITS
     morally
    0.73
     ethically
    0.72
     creatively
    0.70
     politically
    0.68
     culturally
    0.65
     intellectually
    0.64
     personally
    0.62
     academically
    0.60
     emotionally
    0.60
     socially
    0.59
    Activations Density 0.003%

    No Known Activations