© 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. 6219
    Prev
    Next
    INDEX
    Explanations

    phrases related to data presentation and referencing in academic or analytical contexts

    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
    ierr
    -0.60
     innamor
    -0.56
     순
    -0.56
    رر
    -0.55
     oyn
    -0.55
    cierre
    -0.54
     permeability
    -0.53
     Permeability
    -0.52
    fmt
    -0.52
     foot
    -0.52
    POSITIVE LOGITS
     kasarigan
    0.96
    IntoConstraints
    0.90
    ThroughAttribute
    0.86
    ViewFeatures
    0.82
     nakalista
    0.82
    +#+#
    0.80
    vábbi
    0.77
    WebServlet
    0.76
     dAtA
    0.75
    hipster
    0.75
    Activations Density 0.224%

    No Known Activations