© 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. 5-CLT-HP
    7. 94853
    Prev
    Next
    INDEX
    Explanations

    introductory/descriptions

    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
    TagMode
    -0.75
     kasarigan
    -0.68
     gynhyrchwyd
    -0.66
    دانشنامهٔ
    -0.63
    PerformLayout
    -0.62
     disambiguazione
    -0.61
    verwijspagina
    -0.61
     uParam
    -0.61
    はじめに
    -0.61
     typelib
    -0.60
    POSITIVE LOGITS
    TagHelper
    0.59
     we
    0.56
     are
    0.55
    borderSide
    0.53
    IndentedString
    0.52
    ,
    0.50
    ValueGeneration
    0.47
     corresponden
    0.46
    RunWith
    0.46
    Suggested
    0.46
    Activations Density 0.000%

    No Known Activations