© 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. 0-CLT-HP
    7. 42398
    Prev
    Next
    INDEX
    Explanations

    Proton

    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
     enfans
    -0.97
     grecque
    -0.94
    adaptiveStyles
    -0.94
     religieuses
    -0.92
     chré
    -0.90
     fidèles
    -0.90
    InjectAttribute
    -0.88
     blessés
    -0.88
     avoient
    -0.87
     Grecs
    -0.86
    POSITIVE LOGITS
    ing
    1.00
    ation
    0.89
    ary
    0.81
    ous
    0.78
    ally
    0.76
    ative
    0.73
    al
    0.71
    ate
    0.70
    ings
    0.70
    ting
    0.70
    Activations Density 1.567%

    No Known Activations