© 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. 6350
    Prev
    Next
    INDEX
    Explanations

    color specifications in code, particularly in hex format

    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
    full
    -0.56
     
    -0.54
     images
    -0.51
     “
    -0.47
     full
    -0.47
     round
    -0.47
    ing
    -0.46
    all
    -0.46
    <i>
    -0.45
    Full
    -0.45
    POSITIVE LOGITS
     EconPapers
    1.01
     Roskov
    0.97
    webElementXpaths
    0.93
    /*
    0.90
    ViewFeatures
    0.87
     Rptr
    0.85
    хьтан
    0.85
     lenker
    0.82
     ISNI
    0.81
    ScopeManager
    0.78
    Activations Density 0.023%

    No Known Activations