© 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. 22-RES-MATRYOSHKA-DC
    7. 3128
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and references to life

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     ―――――
    -0.90
     disambiguazione
    -0.88
     ་་
    -0.85
     occasioned
    -0.79
    Herzliche
    -0.75
    adpleegd
    -0.73
     miſ
    -0.72
     leſs
    -0.71
    ^(@)
    -0.70
     geleg
    -0.69
    POSITIVE LOGITS
     truly
    0.68
    жели
    0.64
    快速的
    0.63
     данный
    0.63
     réellement
    0.60
     unfortunately
    0.60
     literalmente
    0.60
     clairement
    0.59
     blatantly
    0.59
    非常的
    0.58
    Activations Density 0.737%

    No Known Activations