© 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. 31119
    Prev
    Next
    INDEX
    Explanations

    patterns related to visual elements or layouts in a structured 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
    Not in Any Lists

    No Comments

    Negative Logits
    !*\
    -1.08
    AsUp
    -0.92
    abestanden
    -0.90
    mybatisplus
    -0.87
     bArr
    -0.83
     Meksiku
    -0.82
    mgang
    -0.81
    vaart
    -0.81
    DrawerToggle
    -0.81
    Composable
    -0.80
    POSITIVE LOGITS
              
    1.18
    +#+
    0.91
     ujednoznacz
    0.71
     pleaſure
    0.71
    }:${
    0.71
     //$
    0.71
     Wolken
    0.71
     Fides
    0.69
     Cæsar
    0.66
     purpoſe
    0.65
    Activations Density 0.045%

    No Known Activations