© 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. 38348
    Prev
    Next
    INDEX
    Explanations

    crystalline

    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
    inducing
    -0.57
     Sidney
    -0.54
    Sidney
    -0.48
    crystalline
    -0.45
     Schweitzer
    -0.45
    UMBIA
    -0.44
    JAKARTA
    -0.44
    }{*}{
    -0.43
    stappen
    -0.43
    HasForeignKey
    -0.43
    POSITIVE LOGITS
    aarrggbb
    0.75
    دانشنامهٔ
    0.71
     calendriers
    0.65
    >--}}
    0.63
    osoba
    0.62
    $.
    
    0.60
     lccn
    0.60
    justed
    0.60
     Dinah
    0.60
     Entdecke
    0.59
    Activations Density 0.064%

    No Known Activations