© 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. 1-CLT-HP
    7. 11872
    Prev
    Next
    INDEX
    Explanations

    acer

    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
    acer
    -2.20
    ACER
    -1.16
     acer
    -0.92
    Acer
    -0.76
     Acer
    -0.68
    ace
    -0.59
    acing
    -0.58
     "..\..\..\
    -0.57
    
    -0.56
    amaha
    -0.54
    POSITIVE LOGITS
     препратки
    0.57
     StringTokenizer
    0.56
    es
    0.56
     createSlice
    0.55
     EnglishChoose
    0.54
    b
    0.54
    esity
    0.52
    Хьажоргаш
    0.50
    nologies
    0.47
    تری
    0.46
    Activations Density 0.011%

    No Known Activations