© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1728
    Prev
    Next
    INDEX
    Explanations

    é

    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
     Benson
    -0.60
     Hamilton
    -0.59
     Jones
    -0.58
     mit
    -0.55
     Harris
    -0.55
     op
    -0.54
     du
    -0.53
     Lewis
    -0.53
     Har
    -0.52
    %)$
    -0.52
    POSITIVE LOGITS
     itſelf
    1.06
     Diſ
    1.04
     Monfieur
    1.01
     myſelf
    0.98
     Cæsar
    0.97
     Shakspeare
    0.94
     Theſe
    0.93
     Anſ
    0.91
     définiti
    0.91
     Reſ
    0.90
    Activations Density 0.233%

    No Known Activations