© 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. 31875
    Prev
    Next
    INDEX
    Explanations

    references to scenes in a graphical or game context

    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
    ostante
    -0.80
    RetentionPolicy
    -0.74
    multer
    -0.71
    úgó
    -0.66
     strane
    -0.65
    hematical
    -0.64
    üyük
    -0.63
     individuales
    -0.63
    SharedCtor
    -0.61
    ługi
    -0.61
    POSITIVE LOGITS
     scene
    2.03
     SCENE
    2.03
     scenes
    2.02
     Scene
    1.92
     Scenes
    1.80
    scene
    1.72
    Scenes
    1.68
    SCENE
    1.67
    Scene
    1.60
    SceneManagement
    1.55
    Activations Density 0.008%

    No Known Activations