© 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. 3513
    Prev
    Next
    INDEX
    Explanations

    terms related to proxy services and settings

    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
     /\.(
    -0.80
     Melton
    -0.79
     ThemeData
    -0.78
     sapore
    -0.75
    achet
    -0.74
     Blackman
    -0.73
     Volta
    -0.72
    íritu
    -0.71
    WebVitals
    -0.69
     Elden
    -0.69
    POSITIVE LOGITS
     proxy
    1.88
    Proxy
    1.83
     Proxy
    1.81
    proxy
    1.80
    PROXY
    1.60
     proxies
    1.50
    proxies
    1.34
    Prox
    1.28
     Prox
    1.27
     代理
    1.23
    Activations Density 0.010%

    No Known Activations