© 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. 2768
    Prev
    Next
    INDEX
    Explanations

    Beginnings/Starting

    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
    AccessorTable
    -0.71
    Tembelea
    -0.69
     дописавши
    -0.66
     AssemblyCulture
    -0.63
     Numerade
    -0.57
    :].
    -0.57
     CreateTagHelper
    -0.57
    BeginInit
    -0.57
    SBATCH
    -0.56
    WebControls
    -0.55
    POSITIVE LOGITS
     all
    0.68
     just
    0.53
    everybody
    0.50
     everybody
    0.50
     StatelessWidget
    0.49
    all
    0.48
     everyone
    0.47
     scatola
    0.47
    alnız
    0.46
    BeforeAll
    0.46
    Activations Density 0.003%

    No Known Activations