© 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. 5-CLT-HP
    7. 97174
    Prev
    Next
    INDEX
    Explanations

    text snippets

    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
    MLLoader
    -0.84
    AccessorTable
    -0.67
    ReusableCell
    -0.66
    ANTLR
    -0.66
    BeginContext
    -0.64
    MENAFN
    -0.63
     HttpNotFound
    -0.63
    tvguidetime
    -0.62
     SqlCommand
    -0.62
    awtextra
    -0.61
    POSITIVE LOGITS
     the
    0.51
    AndEndTag
    0.44
     marchandises
    0.42
    isEmail
    0.40
     town
    0.39
     őket
    0.38
     Canada
    0.38
     Ontario
    0.38
    binden
    0.38
    hetics
    0.38
    Activations Density 0.002%

    No Known Activations