© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7755
    Prev
    Next
    INDEX
    Explanations

    references to childhood or childhood-related experiences

    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
    Negative Logits
     systems
    -0.52
    billon
    -0.52
    判
    -0.51
     oxigen
    -0.49
     son
    -0.48
     Prest
    -0.48
     older
    -0.47
    Son
    -0.47
    Regi
    -0.47
    ائن
    -0.47
    POSITIVE LOGITS
     childhood
    3.22
     Childhood
    2.89
    Childhood
    2.88
     boyhood
    2.22
     Kindheit
    2.05
     infancia
    1.91
     infância
    1.84
    enfance
    1.76
     enfance
    1.73
    童年
    1.58
    Activations Density 0.009%

    No Known Activations