© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90940
    Prev
    Next
    INDEX
    Explanations

    prefixes

    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
    un
    -0.70
    actionMode
    -0.66
    Message
    -0.64
     craft
    -0.62
     MESSAGE
    -0.61
    essage
    -0.58
    usermodel
    -0.58
    mess
    -0.57
     scolas
    -0.57
    MESS
    -0.56
    POSITIVE LOGITS
    tagHelperRunner
    0.60
     CURIAM
    0.57
    BeginContext
    0.56
    ьаж
    0.54
    SpringBootTest
    0.54
     OFDb
    0.50
    sy
    0.49
    ages
    0.48
    ificance
    0.47
    viewWillAppear
    0.44
    Activations Density 0.137%

    No Known Activations