© 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. 40554
    Prev
    Next
    INDEX
    Explanations

    mediator

    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
     ainfi
    -0.91
     religieuses
    -0.78
     Jefus
    -0.77
     Monfieur
    -0.77
     présidenti
    -0.76
    CppCodeGen
    -0.75
     colorés
    -0.75
     voici
    -0.75
     Efq
    -0.75
     tombé
    -0.73
    POSITIVE LOGITS
     Al
    0.54
    e
    0.53
    a
    0.51
    homonymie
    0.50
    o
    0.50
     Fre
    0.50
     Ho
    0.49
     Ap
    0.49
     TestBed
    0.48
     Mug
    0.47
    Activations Density 0.061%

    No Known Activations