© 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. 15917
    Prev
    Next
    INDEX
    Explanations

    technical components related to XML schema definitions in project metadata

    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
    følgelig
    -0.58
    RenderAtEndOf
    -0.56
     contextLoads
    -0.56
    grant
    -0.48
     dår
    -0.48
     bättre
    -0.46
    Grants
    -0.46
     grant
    -0.46
     صوتيه
    -0.46
    ftagPool
    -0.46
    POSITIVE LOGITS
    TagMode
    0.88
    sidemargin
    0.78
    hoeddwyd
    0.70
    SequentialGroup
    0.69
    IntoConstraints
    0.69
    NameInMap
    0.68
    RegressionTest
    0.68
    JsonHelper
    0.68
    Viitteet
    0.67
    ieteur
    0.65
    Activations Density 0.005%

    No Known Activations