© 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. 4880
    Prev
    Next
    INDEX
    Explanations

    do

    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
     الحره
    -0.59
     a
    -0.56
     وتسجيلات
    -0.52
     صوتيه
    -0.50
    단
    -0.47
    UpInside
    -0.47
    fileID
    -0.46
    psy
    -0.45
    bag
    -0.45
    уда
    -0.44
    POSITIVE LOGITS
    __).
    0.69
    Abitanti
    0.65
    Obrázky
    0.63
    kloped
    0.60
    Datuak
    0.60
     <<<<<<<<<<<<<<
    0.58
    scribers
    0.57
     سكانية
    0.57
     AssemblyTitle
    0.57
    TintMode
    0.56
    Activations Density 0.002%

    No Known Activations