© 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. 5-CLT-HP
    7. 94086
    Prev
    Next
    INDEX
    Explanations

    Acronyms, names, and places

    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
    ReusableCell
    -0.53
     protoimpl
    -0.53
    vello
    -0.52
    ]?.
    -0.51
     WaitForSeconds
    -0.51
    OrNil
    -0.49
     AppCompat
    -0.48
     Ce
    -0.48
     ModelExpression
    -0.48
     propOrder
    -0.47
    POSITIVE LOGITS
    Hentet
    0.65
    elemField
    0.60
     noDo
    0.59
    zeera
    0.57
     للمعارف
    0.57
     مشين
    0.56
    gameserver
    0.55
     erbjud
    0.54
    EndGlobalSection
    0.54
     nahilalakip
    0.54
    Activations Density 0.002%

    No Known Activations