© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97234
    Prev
    Next
    INDEX
    Explanations

    command-line tools, networking

    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
     girasol
    -0.39
    ContextHolder
    -0.38
    teni
    -0.37
    USH
    -0.37
    bus
    -0.36
     trás
    -0.36
     Preservation
    -0.36
     CWE
    -0.36
    glGen
    -0.35
    branches
    -0.35
    POSITIVE LOGITS
     intptr
    0.79
    awtextra
    0.77
     ivelany
    0.77
    tagHelperRunner
    0.76
     متعلقه
    0.75
     myſelf
    0.75
     שוליים
    0.73
     تضيفلها
    0.72
     سكانية
    0.71
    parsedMessage
    0.71
    Activations Density 0.005%

    No Known Activations