© 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. 4-CLT-HP
    7. 684
    Prev
    Next
    INDEX
    Explanations

    with

    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
    AndEndTag
    -0.81
    tagHelperRunner
    -0.81
     dAtA
    -0.74
    OGND
    -0.73
    rawDesc
    -0.73
     ویکی‌پدیا
    -0.71
     mergeFrom
    -0.69
    цездатний
    -0.66
    jspb
    -0.66
    SourceChecksum
    -0.65
    POSITIVE LOGITS
     a
    0.54
     professionals
    0.53
     companies
    0.53
    professionals
    0.52
     corporations
    0.51
     Professionals
    0.51
     contractors
    0.50
     organizations
    0.48
     individuals
    0.48
     organisations
    0.48
    Activations Density 0.003%

    No Known Activations