© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3329
    Prev
    Next
    INDEX
    Explanations

    bung

    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
     تانيه
    -0.49
     thư
    -0.48
     Gaps
    -0.48
     Gap
    -0.47
    CompilerServices
    -0.47
    charCode
    -0.47
    NOPQRST
    -0.45
    Gap
    -0.45
     adel
    -0.45
    amd
    -0.45
    POSITIVE LOGITS
     beginnetje
    0.66
     дописавши
    0.65
    rungsseite
    0.62
    tagHelperRunner
    0.60
    uvwxyz
    0.58
    ictwo
    0.57
    findpost
    0.55
     hierogly
    0.55
    IUrlHelper
    0.54
    HttpPut
    0.54
    Activations Density 0.000%

    No Known Activations