© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92387
    Prev
    Next
    INDEX
    Explanations

    names and custody

    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
    eson
    -1.21
    +#+#
    -1.01
     BoxFit
    -0.87
    تقاوى
    -0.83
    named
    -0.81
    RenderAtEndOf
    -0.73
    tagHelperRunner
    -0.72
    AndEndTag
    -0.71
     صوتيه
    -0.71
    ribune
    -0.71
    POSITIVE LOGITS
    pto
    0.44
     tri
    0.43
    cookieParser
    0.43
     đà
    0.41
    ay
    0.41
     Hayward
    0.40
     καθ
    0.40
    -
    0.40
    phère
    0.39
    
    0.39
    Activations Density 0.307%

    No Known Activations