© 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. 14907
    Prev
    Next
    INDEX
    Explanations

    an

    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
     AssemblyCulture
    -1.23
    fjspx
    -1.19
    الإنجليزية
    -1.12
    tagHelperRunner
    -1.08
     disambiguazione
    -1.07
    AddHtmlAttribute
    -1.07
     ComVisible
    -1.05
     GenerationType
    -1.05
    +#+#
    -1.03
    parsedMessage
    -1.03
    POSITIVE LOGITS
     
    0.68
    y
    0.65
    t
    0.57
    n
    0.56
     in
    0.56
     is
    0.54
     with
    0.53
     long
    0.53
    .
    0.52
     li
    0.52
    Activations Density 0.065%

    No Known Activations