© 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. 19595
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of inventions or devices

    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
     kasarigan
    -0.65
    AndEndTag
    -0.50
    }();
    -0.50
    tut
    -0.47
    MethodImpl
    -0.45
    polazione
    -0.45
    évaluateur
    -0.43
    ruik
    -0.43
     mContext
    -0.43
    bower
    -0.42
    POSITIVE LOGITS
    udnio
    0.66
    +#+#
    0.66
    writeField
    0.64
     surla
    0.60
    AntiForgeryToken
    0.60
    SharedCtor
    0.60
    躇
    0.58
    ↘
    0.58
    Personensuche
    0.57
    }{*}{
    0.57
    Activations Density 0.076%

    No Known Activations