© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 2041
    Prev
    Next
    INDEX
    Explanations

    technology, product descriptions

    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
    popular
    -1.28
    Popular
    -1.16
     popular
    -1.14
     saites
    -1.14
     Popular
    -1.05
     OFDb
    -1.05
     Meksiku
    -1.02
     POPULAR
    -0.97
     populaire
    -0.94
     pinulongan
    -0.92
    POSITIVE LOGITS
    ed
    0.88
    s
    0.82
    i
    0.71
    a
    0.69
    e
    0.67
     in
    0.59
     and
    0.59
     mid
    0.58
    eth
    0.57
     T
    0.56
    Activations Density 0.558%

    No Known Activations