© 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. 92138
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     Waray
    -0.58
    TestRunner
    -0.57
    Și
    -0.56
    发表于
    -0.56
    Manfaat
    -0.56
    FormState
    -0.56
    AndEndTag
    -0.55
    Kesimpulan
    -0.55
    Kelebihan
    -0.54
     disciple
    -0.54
    POSITIVE LOGITS
     it
    0.63
     there
    0.59
    andinav
    0.52
    avir
    0.50
     Meksiku
    0.50
     There
    0.49
     means
    0.48
    ifoli
    0.47
    similiano
    0.47
    人们
    0.47
    Activations Density 0.012%

    No Known Activations