© 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. 2696
    Prev
    Next
    INDEX
    Explanations

    Android code generation

    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
     a
    -0.57
    createClass
    -0.55
    :')
    -0.55
    SOUNDBITE
    -0.54
     jangka
    -0.53
    :")
    -0.52
    |}{$
    -0.52
     LUMP
    -0.51
     tää
    -0.50
     siebie
    -0.50
    POSITIVE LOGITS
    /**
    0.67
     to
    0.62
     BoxFit
    0.60
    WriteTagHelper
    0.60
    DoubleQuotes
    0.59
    bootstrapcdn
    0.59
     intervening
    0.54
    StoryboardSegue
    0.54
    UnknownFields
    0.54
    GEBURTSDATUM
    0.53
    Activations Density 0.003%

    No Known Activations