© 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. 43390
    Prev
    Next
    INDEX
    Explanations

    invalid forbidden handshake

    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
     CreateTagHelper
    -1.17
     Wikispecies
    -1.05
    +#+#
    -1.00
     disambiguazione
    -0.96
    sizeCache
    -0.91
     devenus
    -0.91
     ineligible
    -0.89
     direta
    -0.89
     impunity
    -0.89
    aarrggbb
    -0.88
    POSITIVE LOGITS
    ly
    2.05
    LY
    1.10
    s
    0.97
    ment
    0.96
    mente
    0.90
    ting
    0.88
    nya
    0.85
    了
    0.84
    fully
    0.83
    tably
    0.83
    Activations Density 0.093%

    No Known Activations