© 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. 40070
    Prev
    Next
    INDEX
    Explanations

    designation, phased

    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
     designations
    -1.25
     designation
    -1.14
     Designation
    -1.08
     négociations
    -0.96
    ſelves
    -0.96
     fidé
    -0.88
     photolibrary
    -0.86
    ğından
    -0.85
     varandra
    -0.84
     Efq
    -0.84
    POSITIVE LOGITS
     of
    0.96
     in
    0.94
     to
    0.78
    .
    0.77
    ,
    0.73
     that
    0.71
     (
    0.69
     for
    0.65
    -
    0.63
     with
    0.62
    Activations Density 0.034%

    No Known Activations