© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 93880
    Prev
    Next
    INDEX
    Explanations

    Any

    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
    Any
    -0.79
     Any
    -0.70
    All
    -0.60
    Some
    -0.58
    Someone
    -0.56
    ANY
    -0.56
     Some
    -0.56
    Your
    -0.54
     Someone
    -0.53
    ALL
    -0.50
    POSITIVE LOGITS
     Of
    0.85
     of
    0.77
    place
    0.77
     InputDecoration
    0.76
    time
    0.75
     other
    0.74
    Of
    0.71
    BagLayout
    0.71
     sort
    0.71
    rawDesc
    0.71
    Activations Density 1.543%

    No Known Activations