© 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. 32395
    Prev
    Next
    INDEX
    Explanations

    phrases indicating supportive roles

    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
    ſelves
    -0.88
    ſelf
    -0.86
     Efq
    -0.74
     Anſ
    -0.73
     Majefty
    -0.73
     Houſe
    -0.73
     itſelf
    -0.73
     Diſ
    -0.72
     purpoſe
    -0.71
     ſtand
    -0.68
    POSITIVE LOGITS
    Autoritní
    0.55
    Erreferentziak
    0.54
     []);
    0.52
    principalTable
    0.51
     and
    0.50
    >();
    0.50
     Conservatory
    0.50
    ”
    0.50
    enumii
    0.48
     -
    0.48
    Activations Density 0.039%

    No Known Activations