© 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. 96359
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    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
     tartalomajánló
    -0.72
    ContentAlignment
    -0.63
     découver
    -0.62
     beginnetje
    -0.61
     Codable
    -0.60
    脚注の使い方
    -0.60
    afficheront
    -0.60
    GraphicsUnit
    -0.59
    Tē
    -0.58
     Мексичка
    -0.57
    POSITIVE LOGITS
     fifth
    0.64
    Kanpo
    0.59
     third
    0.59
     fourth
    0.57
    fourth
    0.54
    Factories
    0.54
     ninth
    0.54
    third
    0.52
     seventh
    0.50
     biri
    0.48
    Activations Density 0.002%

    No Known Activations