© 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. 0-CLT-HP
    7. 41833
    Prev
    Next
    INDEX
    Explanations

    Confederation

    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
     nakalista
    -0.82
     >=",
    -0.76
    :✨
    -0.71
     للاسماء
    -0.69
     pinulongan
    -0.69
     defaultstate
    -0.68
    Rüyada
    -0.68
    GEBURTSDATUM
    -0.68
    AndEndTag
    -0.64
    
    -0.63
    POSITIVE LOGITS
     Working
    0.54
     Living
    0.52
     Flight
    0.49
    thenia
    0.45
    idorm
    0.44
     '.';
    0.44
     sinyal
    0.44
     How
    0.44
     oči
    0.44
    working
    0.43
    Activations Density 0.344%

    No Known Activations