© 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. 10042
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional hardship and appeals for understanding and support

    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
    .*")]
    -0.73
     defaultstate
    -0.67
    ThroughAttribute
    -0.67
    RenderAtEndOf
    -0.65
     {?>
    -0.63
    âtel
    -0.62
    MigrationBuilder
    -0.61
    InputTagHelper
    -0.57
    SerializedSize
    -0.57
    曖昧さ回避
    -0.56
    POSITIVE LOGITS
     IPA
    0.52
    bulin
    0.47
     estekak
    0.46
    ✨:
    0.43
    ύτε
    0.43
    rood
    0.43
    seid
    0.43
     secondary
    0.42
     épo
    0.41
    "]}
    0.41
    Activations Density 0.178%

    No Known Activations