© 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. 5-CLT-HP
    7. 92734
    Prev
    Next
    INDEX
    Explanations

    references

    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
    NameInMap
    -0.73
    MemoryWarning
    -0.68
     protoimpl
    -0.64
     становника
    -0.62
    تقاوى
    -0.61
    jspx
    -0.60
    KEYCODE
    -0.60
    GEBURTSDATUM
    -0.60
     mergeFrom
    -0.60
     وتسجيلات
    -0.59
    POSITIVE LOGITS
     to
    0.58
     replacing
    0.52
     commission
    0.48
     wanting
    0.48
     decentral
    0.47
     his
    0.46
    ods
    0.45
     abroad
    0.45
     restoring
    0.45
     sustainability
    0.44
    Activations Density 0.014%

    No Known Activations