© 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. 1-CLT-HP
    4. 12028
    Prev
    Next
    INDEX
    Explanations

    threshold

    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
     Isles
    -0.94
     isles
    -0.65
     مشين
    -0.63
    adə
    -0.62
    setVerticalGroup
    -0.59
    ">//
    -0.55
     Dale
    -0.55
    Atsauces
    -0.55
    oredCriteria
    -0.54
    ьаж
    -0.54
    POSITIVE LOGITS
    HttpFoundation
    0.56
    specialchars
    0.54
    amation
    0.48
     (()
    0.48
    ביוגרפיה
    0.47
    sze
    0.47
    */].
    0.47
    yla
    0.47
    yce
    0.47
    ting
    0.47
    Activations Density 0.099%

    No Known Activations