Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44934
    Prev
    Next
    INDEX
    Explanations

    swift

    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
     rafraî
    -0.82
     GenerationType
    -0.75
     barnen
    -0.73
     picioare
    -0.71
     refreshing
    -0.70
     FetchType
    -0.70
     Refresh
    -0.69
    HideFlags
    -0.68
     stället
    -0.68
     freshen
    -0.68
    POSITIVE LOGITS
    ness
    0.85
    iness
    0.68
    ingly
    0.67
    ners
    0.64
    ches
    0.63
    nes
    0.62
    ens
    0.60
    rops
    0.60
    ers
    0.57
    ів
    0.57
    Activations Density 1.566%

    No Known Activations