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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 986
    Prev
    Next
    INDEX
    Explanations

    website/programming

    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
     later
    -0.47
     round
    -0.46
     only
    -0.45
     score
    -0.45
     scoring
    -0.44
     alone
    -0.44
     comparison
    -0.41
     portal
    -0.41
     beyond
    -0.40
     proof
    -0.40
    POSITIVE LOGITS
     fermés
    0.90
     varandra
    0.87
     stället
    0.85
     prisonniers
    0.81
     colorés
    0.81
     numéros
    0.80
     câbles
    0.79
     spesa
    0.79
     négociations
    0.79
     travailleurs
    0.79
    Activations Density 0.688%

    No Known Activations