© 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. 26022
    Prev
    Next
    INDEX
    Explanations

    elements related to technological advancements and their impacts

    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
    tvguidetime
    -0.78
     للمعارف
    -0.75
    
    -0.70
    Jeografia
    -0.68
    RTEX
    -0.67
     nahilalakip
    -0.67
    новниш
    -0.65
    出版年
    -0.65
    OCCURRED
    -0.63
     transfieras
    -0.62
    POSITIVE LOGITS
     improved
    0.46
    文明
    0.44
     jsonify
    0.43
     Improved
    0.42
    MPA
    0.42
     BufferedWriter
    0.41
     CWE
    0.41
     sophistication
    0.40
    setPixel
    0.40
    colas
    0.40
    Activations Density 0.205%

    No Known Activations