© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10200
    Prev
    Next
    INDEX
    Explanations

    references to the Standard Model of particle physics

    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
     Theſe
    -0.90
     saites
    -0.75
    存于互联网档案馆
    -0.73
     ſind
    -0.71
     myſelf
    -0.71
    IContainer
    -0.71
     Oester
    -0.71
    windowFixed
    -0.70
     CanadaChoose
    -0.68
    InputTagHelper
    -0.68
    POSITIVE LOGITS
    endregion
    0.70
     SM
    0.53
    eno
    0.52
     chuẩn
    0.50
     cương
    0.49
     AspNetCore
    0.49
     As
    0.49
    nos
    0.48
     core
    0.47
     femei
    0.46
    Activations Density 0.006%

    No Known Activations