© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2784
    Prev
    Next
    INDEX
    Explanations

    location or placement

    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
     nakalista
    -0.73
     AttributeSet
    -0.73
    MigrationBuilder
    -0.71
    sizeCache
    -0.69
     فريبيس
    -0.69
     payé
    -0.69
     propOrder
    -0.67
     дописавши
    -0.66
     AssemblyTitle
    -0.65
     artificiales
    -0.63
    POSITIVE LOGITS
     flat
    0.58
     just
    0.57
     over
    0.52
     high
    0.51
     di
    0.49
     medi
    0.49
     correctly
    0.47
     right
    0.47
     rela
    0.46
     equ
    0.45
    Activations Density 0.004%

    No Known Activations