© 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. 2095
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     RoutedEventArgs
    -0.62
    Jegyzetek
    -0.60
    rungsseite
    -0.57
     HasFactory
    -0.57
    DebuggerStep
    -0.54
    XmlAccessType
    -0.51
    crollView
    -0.51
    JvmStatic
    -0.50
    ]")]
    -0.50
    endpush
    -0.50
    POSITIVE LOGITS
     betweenstory
    0.77
     nimic
    0.65
     if
    0.57
    RenderAtEndOf
    0.57
     anything
    0.56
     gdyby
    0.54
     thither
    0.53
    dolu
    0.52
    sterious
    0.52
    StructEnd
    0.50
    Activations Density 0.002%

    No Known Activations