© 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. 1584
    Prev
    Next
    INDEX
    Explanations

    clo

    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
    hood
    -0.64
     Cla
    -0.54
     hood
    -0.54
     amounts
    -0.52
     Com
    -0.50
     Cl
    -0.50
     mer
    -0.49
     figures
    -0.48
    Cla
    -0.48
    न
    -0.48
    POSITIVE LOGITS
    TagMode
    0.85
    s
    0.84
    Portály
    0.83
     varandra
    0.77
    ième
    0.74
     détru
    0.73
     prêtres
    0.72
     chré
    0.71
     dieux
    0.71
    arithmic
    0.71
    Activations Density 0.063%

    No Known Activations