© 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. 1-CLT-HP
    7. 11441
    Prev
    Next
    INDEX
    Explanations

    belongings

    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
     diverse
    -0.69
     autorytatywna
    -0.68
     belongings
    -0.66
     nahilalakip
    -0.65
     nakalista
    -0.59
     gyhoeddwyd
    -0.58
     okuyayım
    -0.57
    Identyfik
    -0.57
    WriteTagHelper
    -0.56
     cherchés
    -0.56
    POSITIVE LOGITS
     range
    0.56
    ViewFeatures
    0.49
    DebuggerStep
    0.47
     number
    0.46
    Související
    0.46
     jsPsych
    0.44
     kind
    0.43
     المكتبه
    0.43
    ly
    0.43
    ties
    0.42
    Activations Density 0.360%

    No Known Activations