© 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. 4-CLT-HP
    4. 4954
    Prev
    Next
    INDEX
    Explanations

    code/structural text

    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
    ρους
    -0.46
    MessageTagHelper
    -0.44
     PSM
    -0.43
     produisons
    -0.41
    blos
    -0.40
     FDP
    -0.40
     pleaſure
    -0.39
    appendChild
    -0.39
    .。
    -0.39
    ">${
    -0.39
    POSITIVE LOGITS
    AndEndTag
    0.74
     "
    0.72
     “
    0.68
    forChild
    0.66
     Roskov
    0.62
     
    0.60
     ["
    0.58
    ьаж
    0.57
    CodeAttribute
    0.57
     ['
    0.57
    Activations Density 0.055%

    No Known Activations