© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 649
    Prev
    Next
    INDEX
    Explanations

    parents

    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
     Dad
    -0.76
    RegressionTest
    -0.69
     Mom
    -0.62
     betweenstory
    -0.60
    Dad
    -0.55
    fromnode
    -0.54
    horesis
    -0.52
     dad
    -0.51
    ValueGenerated
    -0.50
    ביוגרפיה
    -0.46
    POSITIVE LOGITS
    dies
    0.73
    mies
    0.73
    sy
    0.68
    mie
    0.67
    ma
    0.67
    ster
    0.61
     الاطلاع
    0.61
    mys
    0.60
    gie
    0.59
    ſelf
    0.57
    Activations Density 0.005%

    No Known Activations