© 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. 20-CLT-HP
    7. 77306
    Prev
    Next
    INDEX
    Explanations

    text snippets

    np_max-act-logits · 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
    دانشنامهٔ
    -0.76
     مشين
    -0.75
    tagHelperRunner
    -0.73
    хьтан
    -0.65
    انيف
    -0.65
    SpringBootTest
    -0.63
    adpleegd
    -0.62
     endblock
    -0.61
    EndProject
    -0.61
    ValueStyle
    -0.61
    POSITIVE LOGITS
     share
    0.62
     percentage
    0.56
    CompoundButton
    0.52
     Share
    0.51
    Referanser
    0.49
     gọn
    0.49
    исленность
    0.48
    солю
    0.48
     proportion
    0.47
     desglose
    0.47
    Activations Density 0.000%

    No Known Activations