© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2371
    Prev
    Next
    INDEX
    Explanations

    once

    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
     CreateTagHelper
    -0.72
    tagext
    -0.65
     wireType
    -0.61
    <?
    -0.59
     endblock
    -0.58
    SourceChecksum
    -0.55
    okok
    -0.54
    rungsseite
    -0.52
    ModelAndView
    -0.51
     CURIAM
    -0.50
    POSITIVE LOGITS
     Upon
    0.73
     upon
    0.70
    Upon
    0.68
    upon
    0.59
     UPON
    0.56
     '+':
    0.53
     judiciales
    0.53
     snippetHide
    0.52
     up
    0.51
     aisladas
    0.51
    Activations Density 0.009%

    No Known Activations