© 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. 96214
    Prev
    Next
    INDEX
    Explanations

    platinum

    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
    DockStyle
    -0.75
    ỡng
    -0.75
    IntoConstraints
    -0.74
    InstanceState
    -0.71
     contextLoads
    -0.71
     onCancelled
    -0.71
     SMG
    -0.66
    RenderAtEndOf
    -0.66
    sidemargin
    -0.66
    ########.
    -0.66
    POSITIVE LOGITS
     group
    0.79
     grupo
    0.55
    group
    0.54
     groupe
    0.52
     grup
    0.52
    Abitanti
    0.48
     gruppo
    0.47
     grupp
    0.47
     GROUP
    0.46
    équipe
    0.46
    Activations Density 0.004%

    No Known Activations