© 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. 1-CLT-HP
    7. 12042
    Prev
    Next
    INDEX
    Explanations

    Java code

    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
     Healy
    -2.03
     Healey
    -1.26
    ếng
    -0.62
    ositol
    -0.58
    Erstellt
    -0.58
     disponibilités
    -0.56
    ValueStyle
    -0.55
    督
    -0.53
    发表于
    -0.50
     rozs
    -0.50
    POSITIVE LOGITS
    resave
    0.61
     nahilalakip
    0.57
    <bos>
    0.56
    thâu
    0.55
     estekak
    0.55
    ה
    0.54
     estimés
    0.52
    XMLSchema
    0.52
    ")){
    0.51
     архивлан
    0.51
    Activations Density 0.007%

    No Known Activations