© 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. 1-CLT-HP
    4. 13496
    Prev
    Next
    INDEX
    Explanations

    any

    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
     and
    -0.76
     behavior
    -0.68
     color
    -0.65
    behavior
    -0.62
    Behavioral
    -0.60
    favorite
    -0.60
     favorite
    -0.58
    behavioral
    -0.57
     rumored
    -0.57
    PyErr
    -0.56
    POSITIVE LOGITS
     disambiguazione
    0.71
     препратки
    0.68
    tifiable
    0.65
    WriteBarrier
    0.59
     Governments
    0.58
     /\.
    0.54
    ::$_
    0.54
    postcode
    0.52
     Government
    0.51
     UK
    0.51
    Activations Density 0.014%

    No Known Activations