© 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. 0-CLT-HP
    7. 92147
    Prev
    Next
    INDEX
    Explanations

    law

    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
    uttering
    -0.88
     الحره
    -0.74
    uttered
    -0.73
    lik
    -0.67
    IonicModule
    -0.67
     defStyleAttr
    -0.65
    utters
    -0.62
    SuccessListener
    -0.60
    AddField
    -0.58
    EClass
    -0.57
    POSITIVE LOGITS
     بيها
    0.48
    ={({
    0.48
     mergeFrom
    0.48
    teni
    0.47
    eip
    0.47
    ネート
    0.46
    culable
    0.45
    teng
    0.45
    PMailer
    0.45
     ]}
    0.44
    Activations Density 0.213%

    No Known Activations