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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19655
    Prev
    Next
    INDEX
    Explanations

    code or markup related to technical specifications or database actions

    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
    saraba
    -0.65
    WithIOException
    -0.61
    ThemeOverlay
    -0.60
    webElementXpaths
    -0.54
    enumi
    -0.53
     فريبيس
    -0.52
     loose
    -0.52
    ViewFeatures
    -0.52
    posedge
    -0.51
     numerus
    -0.50
    POSITIVE LOGITS
    seamnă
    0.63
    itinéraire
    0.58
     تضيفلها
    0.57
     itſelf
    0.57
     Itself
    0.56
     itself
    0.54
     Herodotus
    0.52
    ècie
    0.51
     adenocarcinoma
    0.50
    IsMutable
    0.50
    Activations Density 0.470%

    No Known Activations