© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73573
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     arşivlendi
    -0.54
    Personensuche
    -0.52
    +#+#
    -0.51
     åt
    -0.43
     résister
    -0.43
    ाहरण
    -0.42
    CppCodeGen
    -0.42
    الإنجليزية
    -0.39
    inerea
    -0.39
    faz
    -0.39
    POSITIVE LOGITS
     capacities
    0.57
     <<<<<<<<<<<<<<
    0.56
    ClientSize
    0.56
    AuthGuard
    0.55
     发表于
    0.54
     Affiliations
    0.54
     Pilipinas
    0.53
    runApp
    0.52
    الحياه
    0.52
     Bhar
    0.52
    Activations Density 0.000%

    No Known Activations