© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2699
    Prev
    Next
    INDEX
    Explanations

    programming/studying

    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
    sidemargin
    -0.59
    multirow
    -0.55
    AccessorTable
    -0.51
    Slf
    -0.46
    DeleteBehavior
    -0.45
     NSCoder
    -0.45
    zeera
    -0.44
    AxisAlignment
    -0.42
    期刊论文
    -0.41
    Зноскі
    -0.40
    POSITIVE LOGITS
     exemplaires
    0.70
    ：
    0.69
    :
    0.69
     pulito
    0.68
     illustrazione
    0.68
     Only
    0.67
     fidélité
    0.66
     préférence
    0.64
     vecka
    0.63
     investissements
    0.62
    Activations Density 0.001%

    No Known Activations