© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40722
    Prev
    Next
    INDEX
    Explanations

    Syria

    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
     rail
    -0.73
    rail
    -0.63
     Rail
    -0.61
    ly
    -0.57
    Rail
    -0.56
    ians
    -0.54
     railing
    -0.52
    Ctl
    -0.52
     ClassNotFound
    -0.51
    lingen
    -0.51
    POSITIVE LOGITS
    XmlAccessorType
    0.75
     Waray
    0.69
    elemField
    0.61
     חיצוניים
    0.61
    oa̍t
    0.60
     թվական
    0.58
     vuitton
    0.57
    SBATCH
    0.57
    badah
    0.57
     виправивши
    0.54
    Activations Density 0.085%

    No Known Activations