© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5021
    Prev
    Next
    INDEX
    Explanations

    separated

    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
     AspNetCore
    -0.62
    lahraga
    -0.59
    RenderAtEndOf
    -0.55
     <<<<<<<<<<<<<<
    -0.54
    _;
    -0.54
    maketitle
    -0.54
    jfree
    -0.52
    onViewCreated
    -0.52
     resourceCulture
    -0.51
    Enllaces
    -0.51
    POSITIVE LOGITS
     from
    0.54
     CreateTagHelper
    0.51
    AddHtmlAttribute
    0.49
     мәкалә
    0.48
     '\\;'
    0.48
    ält
    0.47
    jsonPath
    0.46
    WriteTagHelper
    0.46
    ніципалі
    0.45
    从中
    0.44
    Activations Density 0.001%

    No Known Activations