© 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. 5-CLT-HP
    7. 2660
    Prev
    Next
    INDEX
    Explanations

    with

    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
     pinulongan
    -0.63
     terms
    -0.59
    InstrumentedTest
    -0.59
     conditions
    -0.56
    IntoConstraints
    -0.55
     unfair
    -0.53
     ModelExpression
    -0.50
    存于互联网档案馆
    -0.50
    terms
    -0.49
    \{\\
    -0.49
    POSITIVE LOGITS
    migrationBuilder
    0.58
    SharedCtor
    0.57
    مراجع
    0.57
    ervlak
    0.56
    HomeAsUpEnabled
    0.55
    المراجع
    0.54
     Wegen
    0.52
     conseiller
    0.52
    ंदीखरीदारी
    0.50
    rawDesc
    0.50
    Activations Density 0.003%

    No Known Activations