© 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. 14510
    Prev
    Next
    INDEX
    Explanations

    Professor/periodontal

    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
    RenderAtEndOf
    -0.56
    PyExc
    -0.53
    боли
    -0.49
    ăn
    -0.49
    rrggbb
    -0.49
    >{@
    -0.49
    UPI
    -0.48
     previa
    -0.48
     crutches
    -0.48
    readystatechange
    -0.48
    POSITIVE LOGITS
     Administrativna
    0.64
     myſelf
    0.54
    LabelTagHelper
    0.52
     uſed
    0.52
     uſe
    0.51
     snippetHide
    0.48
     purpoſe
    0.47
     Chrift
    0.45
     himſelf
    0.45
     Tam
    0.45
    Activations Density 0.028%

    No Known Activations