© 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. 42868
    Prev
    Next
    INDEX
    Explanations

    las

    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
    las
    -0.95
     Paglinawan
    -0.90
     isInitialized
    -0.85
    ########.
    -0.84
    istoitu
    -0.84
    fillType
    -0.84
    ThroughAttribute
    -0.84
    存于互联网档案馆
    -0.83
    RegressionTest
    -0.83
    IUrlHelper
    -0.82
    POSITIVE LOGITS
    s
    0.87
    ity
    0.67
    ized
    0.65
    ities
    0.59
    ly
    0.59
    ness
    0.56
    ed
    0.53
    hips
    0.50
    nya
    0.48
    ів
    0.46
    Activations Density 0.411%

    No Known Activations