© 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. 9354
    Prev
    Next
    INDEX
    Explanations

    Darby

    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
     Darby
    -1.27
    GOTREF
    -0.60
    mith
    -0.56
     تضيفلها
    -0.56
    TabIndex
    -0.56
     vPvB
    -0.53
    SpringRunner
    -0.52
     <>",
    -0.52
    opathy
    -0.51
     resourceCulture
    -0.51
    POSITIVE LOGITS
     disambiguazione
    0.59
     enfans
    0.58
    //
    0.55
    infan
    0.52
     Warne
    0.50
    шеб
    0.50
    ">//
    0.49
    Expedia
    0.49
    JspWriter
    0.48
     Wastes
    0.47
    Activations Density 0.129%

    No Known Activations