© 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. 220
    Prev
    Next
    INDEX
    Explanations

    dps

    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
    :✨
    -0.69
     propOrder
    -0.67
    rungsseite
    -0.63
    AndEndTag
    -0.63
    spół
    -0.63
     Roskov
    -0.60
    SourceChecksum
    -0.57
     minde
    -0.57
    WriteTagHelper
    -0.57
     Orche
    -0.56
    POSITIVE LOGITS
     كومونز
    0.50
    ihnachten
    0.47
    TargetApi
    0.47
    yntaxException
    0.43
    cloudf
    0.42
    Telefax
    0.41
    createTextNode
    0.41
    anmoins
    0.41
     facie
    0.41
     refirió
    0.40
    Activations Density 0.001%

    No Known Activations