© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2260
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    enumi
    -0.61
    IsContent
    -0.58
    multicolumn
    -0.57
     Wikispecies
    -0.54
    WebVitals
    -0.51
    
    -0.51
     onOptions
    -0.51
     poisoned
    -0.49
    NUMX
    -0.49
    enumii
    -0.49
    POSITIVE LOGITS
     Wiring
    0.54
     Replacement
    0.52
    Parts
    0.52
     hemsida
    0.52
     Stainless
    0.50
     stället
    0.50
    Replacement
    0.49
     fabriquer
    0.48
    peda
    0.48
     Brake
    0.48
    Activations Density 0.000%

    No Known Activations