© 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. 0-CLT-HP
    7. 42947
    Prev
    Next
    INDEX
    Explanations

    dietary

    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
    RenderAtEndOf
    -0.98
    SharedDtor
    -0.94
     betweenstory
    -0.92
     صوتيه
    -0.90
    berdayakan
    -0.88
    InjectAttribute
    -0.88
    WithIOException
    -0.87
     quæ
    -0.87
    enumi
    -0.83
     necessárias
    -0.82
    POSITIVE LOGITS
    หวัด
    0.46
    hoea
    0.46
    ly
    0.45
     frappe
    0.43
     F
    0.42
    льно
    0.42
     ingen
    0.42
     English
    0.41
    ing
    0.41
     H
    0.41
    Activations Density 0.030%

    No Known Activations