© 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. 12003
    Prev
    Next
    INDEX
    Explanations

    stock and adaptive contexts

    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
     ostavi
    -0.61
    setVerticalGroup
    -0.55
    enumi
    -0.54
     prezen
    -0.54
    ValueStyle
    -0.53
     klart
    -0.52
     étudi
    -0.52
     bakgrund
    -0.50
     inconnu
    -0.49
     ordinaires
    -0.49
    POSITIVE LOGITS
    GHIJKLM
    0.66
    RuleContext
    0.58
    principalColumn
    0.54
    ''');
    0.54
    noinspection
    0.53
     \%$\\
    0.53
    hdfs
    0.52
    ₡
    0.52
    outState
    0.52
    HandlerContext
    0.51
    Activations Density 0.006%

    No Known Activations