© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2254
    Prev
    Next
    INDEX
    Explanations

    common text

    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
    NgModule
    -0.66
    Życiorys
    -0.61
     Unavailable
    -0.56
    ymce
    -0.56
    ,
    -0.54
    CloseOperation
    -0.53
    InputModule
    -0.52
    WebMethod
    -0.51
    symp
    -0.50
    UnusedPrivate
    -0.49
    POSITIVE LOGITS
     canlynol
    0.57
     Darum
    0.55
    ьажоргаш
    0.55
     Efq
    0.54
    +#+#
    0.53
     zufolge
    0.52
     quæ
    0.51
    AlterField
    0.49
    ільки
    0.49
     lesquels
    0.49
    Activations Density 0.004%

    No Known Activations