© 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. 632
    Prev
    Next
    INDEX
    Explanations

    on

    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
    -
    -0.64
    top
    -0.60
    most
    -0.58
     lẻ
    -0.57
     top
    -0.56
    in
    -0.55
    no
    -0.50
     rette
    -0.48
    first
    -0.48
    we
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.79
     affording
    0.79
     ensuring
    0.79
     compensating
    0.77
     guaranteeing
    0.75
     Efq
    0.74
     insuring
    0.74
     CUCET
    0.73
     defeating
    0.73
     specifying
    0.72
    Activations Density 0.209%

    No Known Activations