© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10286
    Prev
    Next
    INDEX
    Explanations

    ular

    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
    MessageTagHelper
    -0.63
     useRouter
    -0.62
    
    -0.58
    onAttach
    -0.52
    gerald
    -0.51
    ::$
    -0.51
     useHistory
    -0.51
    UnknownFields
    -0.50
    SharedDtor
    -0.50
    columnHeader
    -0.50
    POSITIVE LOGITS
     iprot
    0.50
    WriteTagHelper
    0.50
    ----</
    0.50
    Tweets
    0.47
     ambassade
    0.47
     daqui
    0.47
     impeller
    0.46
    tagext
    0.46
     absoluto
    0.46
    ام
    0.45
    Activations Density 0.053%

    No Known Activations