© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5719
    Prev
    Next
    INDEX
    Explanations

    semicolon

    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
     découver
    -0.73
     AssemblyCulture
    -0.73
     câbles
    -0.70
     démocr
    -0.69
     générations
    -0.68
     cœurs
    -0.68
     varandra
    -0.66
     gånger
    -0.66
     Because
    -0.65
    Because
    -0.65
    POSITIVE LOGITS
     don
    0.91
     otherwise
    0.81
     but
    0.75
     do
    0.72
     thank
    0.70
     instead
    0.65
     remember
    0.64
     preferably
    0.63
     chances
    0.63
     pay
    0.63
    Activations Density 0.001%

    No Known Activations