© 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. 14318
    Prev
    Next
    INDEX
    Explanations

    selections of code or actions related to the named elements in a programming 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
     CreateTagHelper
    -1.20
     bills
    -0.78
    oglio
    -0.75
     Medici
    -0.73
     Hogarth
    -0.73
    spania
    -0.73
     Nunn
    -0.73
     Franti
    -0.72
    ranean
    -0.71
     Tilly
    -0.71
    POSITIVE LOGITS
     Sel
    1.68
    Sel
    1.62
     sel
    1.55
     SEL
    1.51
    sel
    1.41
    SEL
    1.40
    Selen
    1.34
     Selena
    1.30
     Selina
    1.23
     Selby
    1.20
    Activations Density 0.008%

    No Known Activations