© 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. 94475
    Prev
    Next
    INDEX
    Explanations

    world

    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
    SharedDtor
    -0.65
    ItemBackground
    -0.63
    openConnection
    -0.63
     otomatig
    -0.61
    FormTagHelper
    -0.60
     global
    -0.60
     retrouvé
    -0.59
    awtextra
    -0.59
    ]]
    -0.55
    prepareStatement
    -0.54
    POSITIVE LOGITS
    ereo
    0.52
     ethnicity
    0.50
    anterie
    0.49
    phrine
    0.49
    Denied
    0.49
     violate
    0.47
     superstition
    0.46
     demolish
    0.45
     humidity
    0.44
     collusion
    0.44
    Activations Density 0.001%

    No Known Activations