© 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. 91600
    Prev
    Next
    INDEX
    Explanations

    importance

    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
    
    -0.74
     насељу
    -0.64
    Архівовано
    -0.63
    SpringBootTest
    -0.63
    Gweler
    -0.61
    sidemargin
    -0.58
     Instrumentation
    -0.57
     Evidence
    -0.57
     orar
    -0.57
    期刊论文
    -0.57
    POSITIVE LOGITS
    UnusedPrivate
    0.66
     ecological
    0.58
     biological
    0.51
     appetites
    0.48
     disambiguazione
    0.48
     physiological
    0.47
    trophic
    0.47
     natural
    0.47
     mucous
    0.46
     चीज़ों
    0.45
    Activations Density 0.004%

    No Known Activations