© 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. 0-CLT-HP
    7. 1375
    Prev
    Next
    INDEX
    Explanations

    names

    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
    makers
    -0.63
     makers
    -0.61
     Makers
    -0.57
    alinga
    -0.54
     Forster
    -0.53
     electrónicos
    -0.53
     Tzu
    -0.50
    erg
    -0.50
     imidlertid
    -0.50
     gezet
    -0.49
    POSITIVE LOGITS
    RunAsync
    0.66
     thrones
    0.63
    endphp
    0.62
     sonne
    0.62
     Houſe
    0.62
     sceptre
    0.62
     DBNull
    0.62
     Pyrene
    0.61
     uſ
    0.60
     himſelf
    0.59
    Activations Density 0.084%

    No Known Activations