© 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. 19816
    Prev
    Next
    INDEX
    Explanations

    specific brand or product names or references related to media and technology

    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
    MessageOf
    -0.81
    QMetaType
    -0.76
     mergeFrom
    -0.76
    twimg
    -0.74
     Roskov
    -0.74
    principalTable
    -0.72
    PreferredItem
    -0.71
    يكب
    -0.71
    LookAnd
    -0.69
    TintMode
    -0.68
    POSITIVE LOGITS
    esgue
    0.77
    binant
    0.59
    úgó
    0.58
    pired
    0.56
    ongevity
    0.55
     Reif
    0.55
    Accessories
    0.54
    sonaro
    0.54
    SequentialGroup
    0.54
    igma
    0.54
    Activations Density 0.234%

    No Known Activations