© 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. 1761
    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
     can
    -1.20
    can
    -0.98
     Can
    -0.91
    Can
    -0.80
     is
    -0.75
     be
    -0.69
     your
    -0.69
     CAN
    -0.62
    all
    -0.58
     können
    -0.57
    POSITIVE LOGITS
     فريبيس
    0.82
     ſind
    0.80
    PreferredItem
    0.79
     uſe
    0.77
     
    0.76
     يتيمه
    0.75
    Autoritní
    0.75
     nahilalakip
    0.75
    <bos>
    0.73
    AsUp
    0.73
    Activations Density 0.099%

    No Known Activations