© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13698
    Prev
    Next
    INDEX
    Explanations

    references to cultured or cultivated cells used in experiments

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    期刊论文
    -0.66
    extAlignment
    -0.60
    lève
    -0.59
    allax
    -0.58
    writeField
    -0.58
    Население
    -0.57
     cappuccio
    -0.56
     festival
    -0.54
     memoized
    -0.53
     forfait
    -0.53
    POSITIVE LOGITS
     cultured
    2.20
     Roskov
    0.63
    __':
    
    0.57
     classy
    0.57
     дописавши
    0.57
     grounding
    0.57
     guile
    0.54
    Cult
    0.54
     upgrade
    0.53
     Cult
    0.53
    Activations Density 0.001%

    No Known Activations