© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72811
    Prev
    Next
    INDEX
    Explanations

    diverse text snippets

    np_max-act-logits · 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
     gouvernements
    -0.57
     âmes
    -0.52
     émissions
    -0.52
     dommages
    -0.50
    Shard
    -0.49
     paysages
    -0.49
    plane
    -0.49
    cillor
    -0.48
     quote
    -0.48
     bienfaits
    -0.48
    POSITIVE LOGITS
    heets
    0.79
    hares
    0.76
    hops
    0.70
    hots
    0.69
    pots
    0.69
    hoots
    0.69
    ets
    0.68
    copes
    0.66
    ites
    0.66
    cans
    0.66
    Activations Density 0.012%

    No Known Activations