© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94982
    Prev
    Next
    INDEX
    Explanations

    functional

    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
    setContentView
    -0.58
    IBarButtonItem
    -0.56
    urbation
    -0.55
    windowFixed
    -0.54
     BoxDecoration
    -0.52
     CURIAM
    -0.52
    piar
    -0.51
     Wiktionnaire
    -0.49
     spic
    -0.48
     convertView
    -0.48
    POSITIVE LOGITS
    rån
    0.69
     fuo
    0.56
     Administrativna
    0.56
    MLLoader
    0.55
    tijden
    0.53
     RVA
    0.52
     religieuses
    0.50
     dieťa
    0.49
    WEBPACK
    0.48
     propOrder
    0.48
    Activations Density 0.005%

    No Known Activations