© 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. 4456
    Prev
    Next
    INDEX
    Explanations

    to

    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
     aspetto
    -0.47
     recevrez
    -0.47
     distanciation
    -0.47
    look
    -0.46
    bato
    -0.45
    optString
    -0.45
    mtrl
    -0.43
    coords
    -0.43
    Pele
    -0.43
     hjäl
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.78
     nahilalakip
    0.65
     ostavi
    0.62
    انيف
    0.62
    RTDA
    0.60
    SpringBootTest
    0.60
     AssemblyTitle
    0.60
    ंदीखरीदारी
    0.57
     beginnetje
    0.56
     CreateTagHelper
    0.55
    Activations Density 0.002%

    No Known Activations