© 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. 4371
    Prev
    Next
    INDEX
    Explanations

    lea

    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
    <bos>
    -0.71
    ,
    -0.50
    ådet
    -0.50
     '\\;'
    -0.49
    mstyle
    -0.47
     الحره
    -0.47
     occidental
    -0.47
     Stoll
    -0.47
    createClass
    -0.47
    Fa
    -0.47
    POSITIVE LOGITS
    ers
    1.67
    er
    1.16
    ERS
    1.12
    ering
    0.96
    ters
    0.91
    ership
    0.90
    ors
    0.85
    erer
    0.83
    erst
    0.79
    lers
    0.79
    Activations Density 0.023%

    No Known Activations