© 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. 2227
    Prev
    Next
    INDEX
    Explanations

    you

    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
    SourceChecksum
    -0.68
    sidemargin
    -0.63
     ferons
    -0.60
     Winaray
    -0.59
     فريبيس
    -0.58
     unknownFields
    -0.57
    HandlerContext
    -0.57
    Хьажоргаш
    -0.56
    SpringBootTest
    -0.56
    🦵
    -0.55
    POSITIVE LOGITS
     Honour
    0.51
     snippetHide
    0.49
     fucks
    0.49
     Gerrard
    0.49
     honour
    0.47
     lynch
    0.46
    hoots
    0.46
     Saxons
    0.46
     separates
    0.46
     Lassen
    0.46
    Activations Density 0.004%

    No Known Activations