© 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. 1-CLT-HP
    7. 14705
    Prev
    Next
    INDEX
    Explanations

    underlying

    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
     thiệu
    -0.68
    orithmic
    -0.58
    RenderAtEndOf
    -0.57
    UnsafeEnabled
    -0.53
    OfWork
    -0.53
     theme
    -0.52
     fråga
    -0.52
     hadapan
    -0.52
     čase
    -0.50
     ArrayAdapter
    -0.49
    POSITIVE LOGITS
     the
    0.63
    webElementGuid
    0.62
     their
    0.56
     these
    0.55
     our
    0.54
    LabelTagHelper
    0.52
    tagHelperRunner
    0.51
     it
    0.50
     your
    0.50
     those
    0.49
    Activations Density 0.012%

    No Known Activations