© 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. 5-CLT-HP
    7. 92887
    Prev
    Next
    INDEX
    Explanations

    now

    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
     learnt
    -0.48
     recognised
    -0.47
    nus
    -0.47
     taught
    -0.46
     devised
    -0.46
    ubert
    -0.45
     advocated
    -0.44
     utilised
    -0.44
    OD
    -0.44
     Introduced
    -0.43
    POSITIVE LOGITS
    addCriterion
    0.88
    RenderAtEndOf
    0.83
     AssemblyProduct
    0.81
    Geplaatst
    0.73
    Personensuche
    0.73
     ComVisible
    0.67
    ędzynarod
    0.66
     سكانية
    0.65
     Chwiliwch
    0.64
    Activités
    0.62
    Activations Density 0.003%

    No Known Activations