© 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. 0-CLT-HP
    7. 41010
    Prev
    Next
    INDEX
    Explanations

    toolkit

    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
     Tool
    -1.21
     TOOL
    -1.13
    Tool
    -1.08
     Tools
    -1.00
     Toolkit
    -0.96
     Toolbox
    -0.94
     TOOLS
    -0.90
    TOOL
    -0.82
    toolbox
    -0.80
    tool
    -0.79
    POSITIVE LOGITS
    <bos>
    0.55
    Hons
    0.54
    DotNetBar
    0.52
    IndentedString
    0.52
     Greater
    0.52
     snippetHide
    0.51
     kom
    0.51
    CppCodeGen
    0.49
    фель
    0.47
     sen
    0.45
    Activations Density 0.349%

    No Known Activations