© 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. 77423
    Prev
    Next
    INDEX
    Explanations

    Random topics

    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
    τύ
    -0.53
    WebVitals
    -0.51
     loa
    -0.49
     leksikon
    -0.49
    Firestore
    -0.47
     Marac
    -0.46
    Equations
    -0.46
    setSuccess
    -0.45
     Bermuda
    -0.43
    الإنجليزية
    -0.43
    POSITIVE LOGITS
     estekak
    0.59
     муніципалі
    0.57
    rungsseite
    0.57
    AndEndTag
    0.56
     Issa
    0.55
    henswürdigkeiten
    0.52
    SpringBootTest
    0.52
    Tembelea
    0.52
    ++]=
    0.51
    Eksteraj
    0.50
    Activations Density 0.006%

    No Known Activations