© 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. 43506
    Prev
    Next
    INDEX
    Explanations

    Research studies and opinions

    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
     avoient
    -1.05
     étoient
    -1.01
    RenderAtEndOf
    -0.95
     Efq
    -0.87
     esternos
    -0.85
    ագրություններ
    -0.78
     démocr
    -0.76
     chré
    -0.75
     Jefus
    -0.75
     âgées
    -0.74
    POSITIVE LOGITS
     clinical
    0.58
     clinically
    0.52
     mean
    0.51
     DNA
    0.50
    Hasta
    0.49
     mol
    0.49
    IUCN
    0.48
     gut
    0.48
     synthase
    0.47
     serum
    0.47
    Activations Density 0.794%

    No Known Activations