© 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. 4954
    Prev
    Next
    INDEX
    Explanations

    much

    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
     refroidissement
    -0.52
     mères
    -0.52
    IElement
    -0.51
    ępo
    -0.47
     ljud
    -0.46
     szolg
    -0.46
     cœurs
    -0.45
     Pair
    -0.45
    webElementXpaths
    -0.45
    ftar
    -0.45
    POSITIVE LOGITS
     to
    0.65
    évaluateur
    0.63
     चीज़ों
    0.59
     OMITBAD
    0.58
    WriteTagHelper
    0.57
    DoubleQuotes
    0.56
    
    0.54
    aritions
    0.52
     vPvB
    0.52
    expandindo
    0.52
    Activations Density 0.002%

    No Known Activations