© 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. 0-CLT-HP
    7. 38422
    Prev
    Next
    INDEX
    Explanations

    grocery

    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
     Majefty
    -1.06
     purpoſe
    -1.03
     myſelf
    -1.02
     Shakspeare
    -1.00
     tranſ
    -0.99
     ſmall
    -0.98
     pleaſure
    -0.98
     neceſſ
    -0.97
     chré
    -0.96
     Cæsar
    -0.96
    POSITIVE LOGITS
     of
    0.65
     in
    0.63
     
    0.59
     for
    0.57
     a
    0.54
    ↵↵
    0.51
    ,
    0.50
     at
    0.48
     part
    0.48
     held
    0.48
    Activations Density 0.830%

    No Known Activations