© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8903
    Prev
    Next
    INDEX
    Explanations

    Pipe/Waveguide

    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
     pipe
    -0.98
    pipes
    -0.93
    pipe
    -0.90
     pipes
    -0.81
     Pipe
    -0.77
    Pipe
    -0.67
    AndEndTag
    -0.66
    دانشنامهٔ
    -0.62
    AnimationsModule
    -0.59
    /**
    -0.59
    POSITIVE LOGITS
     equator
    0.57
     Nazareth
    0.57
     Galilee
    0.54
     theſe
    0.54
     Caucasus
    0.53
     uſ
    0.53
     sark
    0.53
     Landing
    0.52
     kari
    0.52
     anſ
    0.52
    Activations Density 0.032%

    No Known Activations