© 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. 5-CLT-HP
    7. 4379
    Prev
    Next
    INDEX
    Explanations

    include

    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
     усе
    -0.45
    CodeAttribute
    -0.43
    anggil
    -0.42
    Canvas
    -0.39
    couver
    -0.38
    nové
    -0.38
    grande
    -0.38
    ressee
    -0.38
     Davies
    -0.38
    Xy
    -0.37
    POSITIVE LOGITS
    URLException
    0.69
     disambiguazione
    0.67
     виправивши
    0.66
     للاسماء
    0.64
     препратки
    0.64
    RectangleBorder
    0.64
    TargetException
    0.64
    NameValuePair
    0.62
    ביוגרפיה
    0.61
    новниш
    0.60
    Activations Density 0.017%

    No Known Activations