© 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. 5-CLT-HP
    7. 762
    Prev
    Next
    INDEX
    Explanations

    the

    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
    CppCodeGen
    -0.62
     eventdata
    -0.59
     StringTokenizer
    -0.59
     confounded
    -0.58
    URLException
    -0.56
    GLOBALS
    -0.55
    SPONSORED
    -0.54
     initComponents
    -0.53
    DEPREC
    -0.52
     AttributeSet
    -0.51
    POSITIVE LOGITS
     way
    0.88
     interaction
    0.66
     façon
    0.65
     Way
    0.61
    Way
    0.60
     WAY
    0.59
    way
    0.59
    interaction
    0.58
     structure
    0.58
     shape
    0.58
    Activations Density 0.001%

    No Known Activations