© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13824
    Prev
    Next
    INDEX
    Explanations

    basis

    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
    ^(@)
    -0.74
    出版年
    -0.74
    ResponseWriter
    -0.67
     pleaſure
    -0.67
     typelib
    -0.66
     PublicKey
    -0.62
    verwijspagina
    -0.62
    complexContent
    -0.61
     ſtate
    -0.61
    paravant
    -0.59
    POSITIVE LOGITS
     #
    0.46
     ulti
    0.43
    #
    0.43
    timus
    0.43
    AddHtmlAttribute
    0.43
     #(
    0.41
    icher
    0.41
    astian
    0.41
     cabezas
    0.41
    нти
    0.40
    Activations Density 0.001%

    No Known Activations