© 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. 3238
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
     kasarigan
    -1.04
     мәкал
    -0.77
    EndGlobalSection
    -0.77
    itself
    -0.74
    Portale
    -0.72
    SequentialGroup
    -0.71
    省市镇
    -0.69
     Gegenteil
    -0.67
     autorytatywna
    -0.65
    Hozzáférés
    -0.65
    POSITIVE LOGITS
     whom
    0.83
     himself
    0.79
     who
    0.72
    whom
    0.65
     his
    0.63
     personally
    0.58
    这个人
    0.56
     psychologically
    0.49
     dearest
    0.49
     socially
    0.49
    Activations Density 0.263%

    No Known Activations