© 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. 4-CLT-HP
    7. 1426
    Prev
    Next
    INDEX
    Explanations

    article

    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
     Савезне
    -0.78
     ujednoznacz
    -0.74
     CreateTagHelper
    -0.71
     poffe
    -0.70
     fubject
    -0.68
    empio
    -0.68
     dévelo
    -0.66
     esimer
    -0.66
     purpoſe
    -0.65
    MLLoader
    -0.65
    POSITIVE LOGITS
     series
    0.43
    series
    0.43
    umine
    0.40
    multicolumn
    0.37
    unshift
    0.37
    templateUrl
    0.35
     serie
    0.34
     série
    0.33
    spaceBetween
    0.33
     LUMP
    0.33
    Activations Density 0.007%

    No Known Activations