© 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. 92589
    Prev
    Next
    INDEX
    Explanations

    And/According

    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
    npmjs
    -0.62
    ValueGeneration
    -0.61
     consultato
    -0.60
    ]]
    
    -0.60
    '))
    
    -0.60
    :✨
    -0.57
    findpost
    -0.56
     defaultstate
    -0.56
     springfox
    -0.54
    verwijspagina
    -0.54
    POSITIVE LOGITS
     to
    0.91
    dymyr
    0.55
    envolvimento
    0.54
    原标题
    0.54
    ništ
    0.50
    optString
    0.50
    chappement
    0.49
    ayanan
    0.48
     along
    0.48
     Are
    0.47
    Activations Density 0.050%

    No Known Activations