© 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. 1881
    Prev
    Next
    INDEX
    Explanations

    you

    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
     successive
    -0.61
    breaking
    -0.57
     the
    -0.57
     Breaking
    -0.57
     virtual
    -0.56
     Matching
    -0.56
    we
    -0.53
     Platform
    -0.53
     Than
    -0.53
     Rising
    -0.53
    POSITIVE LOGITS
    <bos>
    1.16
    ’
    0.94
    '
    0.90
     Roskov
    0.86
    LookAnd
    0.76
    abestanden
    0.68
     had
    0.65
     initComponents
    0.65
     propOrder
    0.64
     can
    0.63
    Activations Density 0.253%

    No Known Activations