© 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. 625
    Prev
    Next
    INDEX
    Explanations

    (

    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
     above
    -0.81
     ModelExpression
    -0.79
     Савезне
    -0.78
     example
    -0.75
     already
    -0.75
     وتسجيلات
    -0.74
    bibinfo
    -0.69
    frastructure
    -0.69
     means
    -0.69
     almost
    -0.69
    POSITIVE LOGITS
    and
    0.77
    if
    0.76
    it
    0.74
    so
    0.72
    we
    0.72
    or
    0.69
    they
    0.68
    I
    0.66
    you
    0.66
    let
    0.63
    Activations Density 0.019%

    No Known Activations