© 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. 5-CLT-HP
    4. 96390
    Prev
    Next
    INDEX
    Explanations

    software/technical language

    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
     Or
    -0.66
     And
    -0.63
     or
    -0.59
     They
    -0.59
     and
    -0.58
     But
    -0.52
     OR
    -0.52
     We
    -0.51
    Or
    -0.50
     You
    -0.48
    POSITIVE LOGITS
    there
    0.80
    it
    0.79
    with
    0.75
    without
    0.75
    that
    0.73
    this
    0.72
    while
    0.71
    instead
    0.71
    when
    0.71
    if
    0.69
    Activations Density 0.010%

    No Known Activations