© 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. 4-CLT-HP
    7. 2646
    Prev
    Next
    INDEX
    Explanations

    can

    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
    dafx
    -0.65
    Šaltiniai
    -0.62
    UrlResolution
    -0.61
    fjspx
    -0.60
    CreateModel
    -0.57
    ngdoc
    -0.56
    IVEREF
    -0.55
    TagMode
    -0.55
    انيف
    -0.55
     հղումներ
    -0.54
    POSITIVE LOGITS
     Happen
    0.53
     defaultstate
    0.50
    range
    0.50
    happen
    0.50
     dernières
    0.49
     happen
    0.49
    Last
    0.49
    last
    0.48
     שוליים
    0.48
     last
    0.47
    Activations Density 0.003%

    No Known Activations