© 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. 40551
    Prev
    Next
    INDEX
    Explanations

    cords

    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
     cords
    -1.14
    hö
    -0.99
    Chham
    -0.90
    alty
    -0.88
    jsxFileName
    -0.75
     externi
    -0.73
     autorytatywna
    -0.73
     lenker
    -0.73
     Normdatei
    -0.72
    NameInMap
    -0.71
    POSITIVE LOGITS
     cầu
    0.45
    tión
    0.43
    ACTED
    0.43
     tal
    0.41
    ensio
    0.40
    splitlines
    0.40
    arvi
    0.40
    pdp
    0.39
    onSave
    0.39
     friction
    0.39
    Activations Density 1.721%

    No Known Activations