© 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. 1007
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    NOPQRST
    -0.59
    FieldError
    -0.56
    kháu
    -0.53
    MetaType
    -0.52
     Btu
    -0.52
     Heav
    -0.49
    ksesta
    -0.48
     contextLoads
    -0.47
     JpaRepository
    -0.47
     Hah
    -0.46
    POSITIVE LOGITS
    AsUp
    0.76
    AutoScaleMode
    0.69
    хьтан
    0.64
    новниш
    0.59
     LoggerFactory
    0.58
    ,))
    0.54
    textTheme
    0.54
    Rüyada
    0.52
     буенча
    0.52
    )});
    0.50
    Activations Density 0.000%

    No Known Activations