© 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. 16463
    Prev
    Next
    INDEX
    Explanations

    terms related to responses or reactions in various contexts

    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
     AssemblyCulture
    -1.00
     BoxFit
    -0.90
     للمعارف
    -0.85
     itſelf
    -0.84
     quæ
    -0.82
    CppMethod
    -0.82
    ſelves
    -0.81
     Préférences
    -0.81
     Sarm
    -0.80
     myſelf
    -0.79
    POSITIVE LOGITS
     Villanueva
    0.62
    Rujukan
    0.56
     Carrillo
    0.56
    ilo
    0.55
    之力
    0.54
     Murillo
    0.53
     autorytatywna
    0.52
    </i>
    0.51
     its
    0.51
    炮
    0.51
    Activations Density 0.041%

    No Known Activations