© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41775
    Prev
    Next
    INDEX
    Explanations

    code and scientific introductions

    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
    MessageTagHelper
    -0.59
    lit
    -0.57
     AssemblyVersion
    -0.57
    DoubleQuotes
    -0.57
    RectangleBorder
    -0.55
     Temperance
    -0.54
    GOTREF
    -0.53
     furnished
    -0.52
     Kenyatta
    -0.51
    ọn
    -0.51
    POSITIVE LOGITS
    <bos>
    1.00
    rungsseite
    0.70
    +#+#
    0.66
    ItemBackground
    0.64
    )_/¯
    0.63
     betweenstory
    0.63
    '},
    0.63
     iprot
    0.63
     istr
    0.61
    __':
    0.60
    Activations Density 0.141%

    No Known Activations