© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4187
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparative analysis or contrasts between subjects

    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
    (;;)
    -0.90
     Надо
    -0.88
     guère
    -0.88
    цездатний
    -0.85
     auffi
    -0.82
    <_>
    -0.81
    ^(@)
    -0.80
     daß
    -0.80
     jedenfalls
    -0.79
     ―――――
    -0.78
    POSITIVE LOGITS
     данный
    0.74
     hierbei
    0.71
     içeris
    0.71
     aforementioned
    0.71
     içerisinde
    0.70
     posiada
    0.67
     welcher
    0.67
    masalahan
    0.67
    Lastly
    0.66
     utilizing
    0.65
    Activations Density 3.009%

    No Known Activations