© 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. 0-CLT-HP
    7. 42878
    Prev
    Next
    INDEX
    Explanations

    accessories

    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
    apati
    -0.62
     inégal
    -0.58
     Accessibility
    -0.57
     recollection
    -0.57
     accessibility
    -0.56
     esprits
    -0.56
     sauvages
    -0.54
    getMock
    -0.54
     Apost
    -0.54
     Accessory
    -0.54
    POSITIVE LOGITS
    IsContent
    0.82
    Билгалдахарш
    0.73
    UnusedPrivate
    0.69
    AndEndTag
    0.69
     AssemblyTitle
    0.68
    InjectAttribute
    0.67
    TagHelpers
    0.66
    SharedDtor
    0.64
    ('');
    0.63
     mergeFrom
    0.62
    Activations Density 0.079%

    No Known Activations