© 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. 18091
    Prev
    Next
    INDEX
    Explanations

    phrases that express concern for others

    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
    Negative Logits
    PhysRev
    -0.77
     betweenstory
    -0.70
    setViewportView
    -0.69
    SharedCtor
    -0.67
     estekak
    -0.64
    Personensuche
    -0.63
     Roskov
    -0.62
     fune
    -0.62
     NgModule
    -0.60
    ]<<"
    -0.59
    POSITIVE LOGITS
    ButterKnife
    0.65
    principalColumn
    0.63
    self
    0.58
     those
    0.58
     natt
    0.58
     entire
    0.57
     own
    0.57
     Wicidata
    0.57
     lais
    0.54
    '
    0.54
    Activations Density 0.045%

    No Known Activations