© 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. 4-CLT-HP
    7. 2435
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ItemBackground
    -0.93
     travelling
    -0.75
     arriving
    -0.75
    IntoConstraints
    -0.74
     arrivé
    -0.74
     elettrico
    -0.72
     pauvres
    -0.69
     domestiques
    -0.68
     électroniques
    -0.68
     revolving
    -0.68
    POSITIVE LOGITS
     discuss
    0.62
     talk
    0.60
     experience
    0.55
     listen
    0.55
    setVerticalGroup
    0.51
     chat
    0.47
     hear
    0.46
     partake
    0.46
     trade
    0.45
     witness
    0.45
    Activations Density 0.010%

    No Known Activations