© 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. 97178
    Prev
    Next
    INDEX
    Explanations

    this my

    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
     pinulongan
    -0.56
     spears
    -0.55
     surnames
    -0.55
     pints
    -0.53
     violins
    -0.53
     canoes
    -0.53
     chests
    -0.52
     kayaks
    -0.52
     bicycles
    -0.52
     torches
    -0.52
    POSITIVE LOGITS
     nahilalakip
    0.68
    LIKE
    0.62
    KeySpec
    0.57
    ânea
    0.56
     like
    0.55
    RuleContext
    0.54
    nosť
    0.54
     Institutional
    0.54
    terness
    0.54
    ManagedBean
    0.54
    Activations Density 0.146%

    No Known Activations