© 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. 4-CLT-HP
    7. 505
    Prev
    Next
    INDEX
    Explanations

    is

    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
     ModelExpression
    -0.69
    ItemBackground
    -0.66
     kasarigan
    -0.65
     يتيمه
    -0.64
     متعلقه
    -0.63
    #+#
    -0.62
    webElementXpaths
    -0.62
    RTLD
    -0.57
    ParallelGroup
    -0.56
    HostException
    -0.56
    POSITIVE LOGITS
     to
    0.71
     encountered
    0.55
    UpInside
    0.54
     fallu
    0.52
     disponibilités
    0.52
    ẹo
    0.51
     barres
    0.50
    ities
    0.49
     Encounters
    0.49
     up
    0.48
    Activations Density 0.003%

    No Known Activations