© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39831
    Prev
    Next
    INDEX
    Explanations

    bacteria

    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
    .*")]
    -0.78
    __':
    
    -0.69
    copg
    -0.67
    XmlAccessorType
    -0.65
    GEBURTS
    -0.63
    lices
    -0.62
    ratulations
    -0.62
    dalena
    -0.62
    ocene
    -0.60
     sterile
    -0.60
    POSITIVE LOGITS
    s
    0.94
     kasarigan
    0.61
    sis
    0.60
    sen
    0.56
    ся
    0.55
    sin
    0.52
    sn
    0.50
    یی
    0.50
    sa
    0.48
    ی
    0.48
    Activations Density 0.052%

    No Known Activations