© 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. 3032
    Prev
    Next
    INDEX
    Explanations

    amy

    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
     referenties
    -0.52
    PRNewswire
    -0.48
     pés
    -0.47
    Gemeinde
    -0.46
     partagé
    -0.46
    toHaveBeen
    -0.44
    出版年
    -0.44
    multi
    -0.44
     TextAppearance
    -0.44
    port
    -0.43
    POSITIVE LOGITS
    elemField
    0.73
    enterOuterAlt
    0.71
     CreateTagHelper
    0.63
    RTDA
    0.61
    WireFormatLite
    0.58
     rhestr
    0.58
    AttributeSet
    0.58
     cyanide
    0.57
    scriptId
    0.56
     trs
    0.56
    Activations Density 0.004%

    No Known Activations