© 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. 1-CLT-HP
    7. 11408
    Prev
    Next
    INDEX
    Explanations

    backed

    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
     backed
    -1.38
     backing
    -1.37
     Backing
    -1.16
    backing
    -1.16
    backed
    -1.11
     backs
    -1.09
    Backing
    -1.03
     backers
    -0.84
     виправивши
    -0.79
    IUrlHelper
    -0.79
    POSITIVE LOGITS
     up
    0.63
     down
    0.53
    uiente
    0.49
     off
    0.48
    fiez
    0.48
    NOPQRST
    0.46
    GREES
    0.46
    colgroup
    0.45
    unyi
    0.44
     away
    0.44
    Activations Density 0.034%

    No Known Activations