© 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. 5-CLT-HP
    4. 13
    Prev
    Next
    INDEX
    Explanations

    of

    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
    expandindo
    -1.17
    GEBURTSDATUM
    -1.07
     دیکھیے
    -1.05
    CloseOperation
    -0.99
     autorytatywna
    -0.98
    脚注の使い方
    -0.96
    SharedDtor
    -0.96
    ьаж
    -0.95
    principalColumn
    -0.95
    AsUp
    -0.94
    POSITIVE LOGITS
     ways
    0.62
     "
    0.45
     to
    0.42
     means
    0.41
    .
    0.40
     dichos
    0.40
     «
    0.40
     strategies
    0.38
     “
    0.38
    <b>
    0.37
    Activations Density 0.002%

    No Known Activations