© 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. 1-CLT-HP
    7. 46324
    Prev
    Next
    INDEX
    Explanations

    co

    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
    s
    -0.82
    ting
    -0.54
    currentColor
    -0.53
    sound
    -0.50
    sak
    -0.50
     propOrder
    -0.49
    น
    -0.49
    ت
    -0.48
     Co
    -0.48
    shel
    -0.48
    POSITIVE LOGITS
    ROIT
    0.55
     armées
    0.55
     '\\;'
    0.54
    __*/
    0.53
     aikaa
    0.52
    aarrggbb
    0.52
    ыгана
    0.51
     poffe
    0.50
     peintures
    0.50
    Chham
    0.49
    Activations Density 0.016%

    No Known Activations