Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 384
    Prev
    Next
    INDEX
    Explanations

    understatement

    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
     understatement
    -1.09
    acia
    -0.92
    ilu
    -0.78
    pecific
    -0.69
     hashes
    -0.65
     sqlSession
    -0.65
     Partagez
    -0.64
    TargetApi
    -0.63
     propOrder
    -0.63
    viewDidLoad
    -0.59
    POSITIVE LOGITS
    htub
    0.58
    IVIA
    0.54
    Trama
    0.52
    SharedDtor
    0.51
     bar
    0.50
    奔
    0.49
     SNL
    0.47
     font
    0.47
     напо
    0.47
    İŞ
    0.47
    Activations Density 0.401%

    No Known Activations