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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73863
    Prev
    Next
    INDEX
    Explanations

    formal writing

    np_max-act-logits · 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
    Tembelea
    -0.65
    UnsafeEnabled
    -0.63
    GOTREF
    -0.60
    UserScript
    -0.59
    gameserver
    -0.54
    Personendaten
    -0.52
    SpringBootTest
    -0.50
     }{@
    -0.50
    umbledore
    -0.50
    TypedDataSet
    -0.50
    POSITIVE LOGITS
     BIBSYS
    0.54
     Reporters
    0.52
     Finding
    0.50
     RSSSF
    0.48
    rodu
    0.48
    IUrlHelper
    0.47
    nodoc
    0.47
    oucí
    0.47
     мәкал
    0.46
    arised
    0.46
    Activations Density 0.000%

    No Known Activations