© 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. 4-CLT-HP
    7. 495
    Prev
    Next
    INDEX
    Explanations

    New York

    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
     nakalista
    -0.88
    Ecotoxicity
    -0.64
    ContentAsync
    -0.59
    :]:
    -0.58
    createStatement
    -0.52
    wishlist
    -0.52
    ंदीखरीदारी
    -0.52
     Wicidata
    -0.51
    logrus
    -0.51
    niosek
    -0.50
    POSITIVE LOGITS
    тьяна
    0.50
    PreferredItem
    0.49
    دانشنامهٔ
    0.47
    ास
    0.47
    ifikant
    0.46
    RootElement
    0.46
     [['
    0.45
    انجليز
    0.45
    bitField
    0.44
     Boven
    0.44
    Activations Density 0.001%

    No Known Activations