© 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. 16489
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to installation and system operations

    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
     Escolar
    -0.54
     saada
    -0.48
    ซ์
    -0.48
    ِّ
    -0.48
     vorge
    -0.47
     fiscales
    -0.47
     boste
    -0.46
     držav
    -0.46
     ulang
    -0.46
     podjet
    -0.45
    POSITIVE LOGITS
     الحره
    0.76
    rrggbb
    0.70
    SharedCtor
    0.70
    principalColumn
    0.68
    SharedDtor
    0.67
    Jîn
    0.64
    XmlAccessType
    0.62
    yntaxException
    0.61
    rungsseite
    0.60
    BeginContext
    0.57
    Activations Density 0.453%

    No Known Activations