© 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. 25528
    Prev
    Next
    INDEX
    Explanations

    references to geometric concepts or planes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     McClure
    -0.72
     Hild
    -0.69
     jsPsych
    -0.69
    asts
    -0.64
    sterious
    -0.62
    hips
    -0.62
    matic
    -0.60
    NameInMap
    -0.58
    epam
    -0.58
    kel
    -0.57
    POSITIVE LOGITS
     Plane
    1.24
     PLANE
    1.22
    Plane
    1.21
     planes
    1.09
     Planes
    1.08
     plane
    1.06
    plane
    1.05
    PLANE
    1.05
    Planes
    1.03
    planes
    1.00
    Activations Density 0.012%

    No Known Activations