© 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. 4-CLT-HP
    7. 5028
    Prev
    Next
    INDEX
    Explanations

    work

    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
     their
    -0.74
    }{*}{
    -0.69
    lear
    -0.67
    abestanden
    -0.66
     متعلقه
    -0.65
     CreateTagHelper
    -0.62
    their
    -0.61
     мәкалә
    -0.61
     Bioaccumulative
    -0.60
    fromnode
    -0.59
    POSITIVE LOGITS
     NUKAT
    0.52
    StoryboardSegue
    0.51
    DockStyle
    0.45
     layui
    0.43
    typeorm
    0.43
     publick
    0.42
     againſt
    0.42
    SuppressMessage
    0.42
     pó
    0.42
     AssemblyProduct
    0.42
    Activations Density 0.000%

    No Known Activations