© 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. 4-CLT-HP
    7. 3331
    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
    twimg
    -0.79
    EndGlobalSection
    -0.76
    SpringBootTest
    -0.71
    ̍t
    -0.71
     typelib
    -0.68
    awtextra
    -0.67
     سكانية
    -0.65
     kaarangay
    -0.65
    contentLoaded
    -0.65
     Waray
    -0.65
    POSITIVE LOGITS
    ffen
    0.49
    ilov
    0.49
    Dump
    0.49
    ILIA
    0.48
     use
    0.47
    ßerdem
    0.47
     használat
    0.46
    ImageContext
    0.46
    ftant
    0.45
    Defaults
    0.45
    Activations Density 0.001%

    No Known Activations