© 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. 1-CLT-HP
    7. 12171
    Prev
    Next
    INDEX
    Explanations

    scientific/medical texts

    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
     AssemblyCulture
    -0.75
    RTEE
    -0.53
    ScopeManager
    -0.51
    ed
    -0.49
    CppMethod
    -0.49
    Посилання
    -0.49
     joaat
    -0.48
    Trama
    -0.48
     cuticle
    -0.47
     secco
    -0.47
    POSITIVE LOGITS
    matchCondition
    0.52
     دیکھیے
    0.51
     utafitiHapana
    0.50
     vux
    0.49
    raid
    0.49
    rätt
    0.49
     sahiptir
    0.48
     aikaa
    0.48
    ToEdit
    0.46
     nourriture
    0.46
    Activations Density 0.094%

    No Known Activations