© 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. 4-CLT-HP
    7. 4992
    Prev
    Next
    INDEX
    Explanations

    to

    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
    -0.67
     tungkol
    -0.65
    ंदीखरीदारी
    -0.59
    SharedDtor
    -0.59
     CreateTagHelper
    -0.54
     terhadap
    -0.54
    "]();
    -0.53
     ujednoznacz
    -0.51
    about
    -0.50
     tentang
    -0.50
    POSITIVE LOGITS
     a
    0.75
     the
    0.67
    oraz
    0.55
     your
    0.54
     Процитовано
    0.53
     Dijo
    0.49
    PRWEB
    0.49
     authority
    0.48
     excellence
    0.47
    pearing
    0.47
    Activations Density 0.001%

    No Known Activations