© 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. 4-CLT-HP
    4. 3201
    Prev
    Next
    INDEX
    Explanations

    phone

    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
    RunWith
    -0.71
    Hochspringen
    -0.69
    :✨
    -0.57
    #
    -0.55
     متعلقه
    -0.54
    رشف
    -0.53
     faccia
    -0.53
    ]--;
    -0.53
     שוליים
    -0.52
     Trag
    -0.50
    POSITIVE LOGITS
     to
    0.79
     ready
    0.61
     out
    0.61
     moving
    0.60
     moved
    0.56
     up
    0.56
     off
    0.56
    omock
    0.54
     open
    0.53
     prepared
    0.52
    Activations Density 0.007%

    No Known Activations