© 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. 9636
    Prev
    Next
    INDEX
    Explanations

    semin

    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
    zun
    -1.53
     Zun
    -0.98
     Bioaccumulative
    -0.65
     <<<<<<<<<<<<<<
    -0.64
     AssemblyCulture
    -0.63
     للمعارف
    -0.62
    новниш
    -0.62
    TemporalType
    -0.61
    ValueStyle
    -0.60
    cshtml
    -0.60
    POSITIVE LOGITS
    en
    0.62
    shop
    0.57
    inars
    0.54
    inario
    0.54
    enor
    0.50
    ی
    0.50
    script
    0.47
    alai
    0.46
    inę
    0.46
    mäß
    0.45
    Activations Density 0.096%

    No Known Activations