© 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. 45590
    Prev
    Next
    INDEX
    Explanations

    accent

    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
     desire
    -0.89
    ils
    -0.74
    desire
    -0.73
     Desire
    -0.66
     contained
    -0.65
     replace
    -0.55
     l
    -0.55
     Replace
    -0.52
    Desire
    -0.47
    ceda
    -0.46
    POSITIVE LOGITS
    enumi
    1.01
    tvguidetime
    1.00
    OGND
    0.89
     disambiguazione
    0.88
     utafitiHapana
    0.85
     समीक्षाओं
    0.78
    
    0.76
    ConstraintMaker
    0.75
    Rhestr
    0.74
     تضيفلها
    0.73
    Activations Density 0.060%

    No Known Activations