© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45706
    Prev
    Next
    INDEX
    Explanations

    seabed

    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
     seabed
    -1.59
    
    -0.73
    RetentionPolicy
    -0.68
     cherchés
    -0.67
     ISNI
    -0.66
     chofe
    -0.66
    Pranala
    -0.65
    imek
    -0.64
     nahilalakip
    -0.62
     uſe
    -0.61
    POSITIVE LOGITS
    r
    0.46
    olingo
    0.42
    }=\{
    0.41
    etCode
    0.40
    tricos
    0.40
    дон
    0.40
     Material
    0.40
     Courant
    0.40
    cor
    0.39
    غراف
    0.39
    Activations Density 0.840%

    No Known Activations