© 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. 5-CLT-HP
    7. 92054
    Prev
    Next
    INDEX
    Explanations

    their

    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
     للمعارف
    -0.77
     CreateTagHelper
    -0.71
    AndEndTag
    -0.66
    ThroughAttribute
    -0.62
    Personensuche
    -0.61
     defaultstate
    -0.60
     дописавши
    -0.59
     bezeichneter
    -0.59
     متعلقه
    -0.57
    loride
    -0.57
    POSITIVE LOGITS
     folgte
    0.51
     bő
    0.50
     jsPsych
    0.50
     næste
    0.49
     række
    0.48
     laajenta
    0.47
    :
    0.47
     löyty
    0.46
     näky
    0.46
     palvel
    0.45
    Activations Density 0.001%

    No Known Activations