© 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. 18918
    Prev
    Next
    INDEX
    Explanations

    descriptions of middle-class life and a longing for stability and security

    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
    ühne
    -0.59
    WritableDatabase
    -0.59
     Biôgrafia
    -0.59
    principalColumn
    -0.57
    BufferException
    -0.56
     privées
    -0.56
     esternos
    -0.55
     énergé
    -0.54
    WithIOException
    -0.54
    ########.
    -0.53
    POSITIVE LOGITS
     boring
    0.88
    地味
    0.78
    Boring
    0.77
     mediocrity
    0.77
    boring
    0.77
     mundane
    0.73
     mund
    0.73
     Boring
    0.72
     predictable
    0.71
     placid
    0.69
    Activations Density 0.149%

    No Known Activations