© 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. 0-CLT-HP
    7. 42761
    Prev
    Next
    INDEX
    Explanations

    Simple/beginning coding

    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
     basic
    -1.01
    basic
    -0.88
    addCriterion
    -0.77
     exactamente
    -0.77
     exactly
    -0.75
    Basic
    -0.71
     básica
    -0.71
    exactly
    -0.69
     Basic
    -0.69
     básico
    -0.68
    POSITIVE LOGITS
     thing
    0.49
     shape
    0.46
     {
    0.45
     recipe
    0.44
    BeginInit
    0.44
    ++++++++++++++++
    0.43
     info
    0.43
    SpringRunner
    0.43
    ////////////////
    0.41
     deal
    0.40
    Activations Density 1.575%

    No Known Activations