© 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. 12-RES-MATRYOSHKA-DC
    7. 12063
    Prev
    Next
    INDEX
    Explanations

    expressions indicating relationships and interactions between people

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.59
     initComponents
    -0.49
     plus
    -0.48
     
    -0.47
     "
    -0.45
    rrggbb
    -0.43
    greenrobot
    -0.42
     Königreich
    -0.42
    <eos>
    -0.41
    جمعیت
    -0.41
    POSITIVE LOGITS
    ⓧ
    0.86
     חיצוניים
    0.83
    Geplaatst
    0.79
     Majefty
    0.78
    évaluateur
    0.74
    Климат
    0.72
     sandero
    0.71
    клопе
    0.70
     ſche
    0.70
     itſelf
    0.70
    Activations Density 0.099%

    No Known Activations