© 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. 18762
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or areas associated with "corners."

    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
    databind
    -0.90
    Tikang
    -0.84
     vuitton
    -0.81
    ApiModelProperty
    -0.81
    Datuak
    -0.76
    shein
    -0.75
    ónio
    -0.74
    ApplicationTests
    -0.74
    jaer
    -0.74
     مرئيه
    -0.73
    POSITIVE LOGITS
     corners
    1.59
     corner
    1.56
     Corner
    1.48
    Corner
    1.45
     Corners
    1.41
    corners
    1.39
    Corners
    1.39
    corner
    1.38
     CORNER
    1.29
    CORN
    0.96
    Activations Density 0.009%

    No Known Activations