© 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. 20-CLT-HP
    7. 74897
    Prev
    Next
    INDEX
    Explanations

    Medical and mental health

    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
     StatelessWidget
    -0.86
     GenerationType
    -0.75
    IntoConstraints
    -0.69
     StatefulWidget
    -0.63
    oprecip
    -0.60
     JpaRepository
    -0.59
     AssemblyTitle
    -0.58
     AssemblyVersion
    -0.58
     betweenstory
    -0.58
    posedge
    -0.57
    POSITIVE LOGITS
     α
    0.46
    bootstrapcdn
    0.45
    Sum
    0.43
     חיצוניים
    0.42
     alpha
    0.42
     Sum
    0.42
     sum
    0.42
    α
    0.40
    RenderAtEndOf
    0.40
     sumo
    0.40
    Activations Density 0.001%

    No Known Activations