© 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. 41064
    Prev
    Next
    INDEX
    Explanations

    Latin or Holy

    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
    StoryboardSegue
    -0.67
    tagHelperRunner
    -0.63
    Демографія
    -0.63
     pleaſure
    -0.62
     neceff
    -0.55
     contras
    -0.54
    Hydro
    -0.53
     Hydro
    -0.53
     crocodile
    -0.52
    eleste
    -0.51
    POSITIVE LOGITS
     ProtoMessage
    0.71
     colorés
    0.63
    jspx
    0.60
     artificiales
    0.57
     skrift
    0.56
     spesa
    0.54
     danni
    0.52
     nemici
    0.52
    
    0.52
     sanitaires
    0.52
    Activations Density 0.022%

    No Known Activations