© 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. 0-CLT-HP
    7. 1188
    Prev
    Next
    INDEX
    Explanations

    "1"

    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
     CreateTagHelper
    -0.96
    parsedMessage
    -0.92
    sizeCache
    -0.85
    runApp
    -0.84
    sidemargin
    -0.83
     BoxFit
    -0.82
    fjspx
    -0.82
    })));
    -0.82
     ***!
    -0.81
    تقاوى
    -0.79
    POSITIVE LOGITS
     urb
    0.47
     Berto
    0.46
    ლ
    0.44
    screenWidth
    0.42
     circ
    0.42
     pop
    0.41
    FromArray
    0.41
     Blood
    0.41
    Blood
    0.41
     ع
    0.41
    Activations Density 0.265%

    No Known Activations