© 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. 5-CLT-HP
    7. 93298
    Prev
    Next
    INDEX
    Explanations

    the/a

    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
    +#+#
    -0.71
    avyzd
    -0.66
     CURIAM
    -0.56
     Praça
    -0.52
    wdriver
    -0.52
    बस
    -0.52
     zel
    -0.50
    bildēt
    -0.50
    ніципа
    -0.49
    uminescence
    -0.48
    POSITIVE LOGITS
    ReusableCell
    0.63
     MainAxisSize
    0.62
    principalColumn
    0.56
     nahilalakip
    0.54
    Tikang
    0.52
    interopRequire
    0.50
    AddHtmlAttribute
    0.49
    pyx
    0.49
    AddTagHelper
    0.48
     total
    0.47
    Activations Density 0.008%

    No Known Activations