© 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. 13571
    Prev
    Next
    INDEX
    Explanations

    personal pronouns

    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
     utafitiHapana
    -1.07
    parsedMessage
    -1.03
    UnsafeEnabled
    -0.98
    IsMutable
    -0.94
     kasarigan
    -0.93
     '\\;'
    -0.91
    IsContent
    -0.90
    檚
    -0.88
     Normdatei
    -0.87
    ReusableCell
    -0.87
    POSITIVE LOGITS
    '
    0.98
    ’
    0.93
     are
    0.53
     will
    0.53
     wrote
    0.50
     can
    0.49
     said
    0.49
    `
    0.48
     made
    0.48
     would
    0.47
    Activations Density 0.058%

    No Known Activations