© 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. 11115
    Prev
    Next
    INDEX
    Explanations

    references to wine and cheese in dietary 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
    uevas
    -0.45
     Ver
    -0.44
     Es
    -0.43
    peria
    -0.43
     Qu
    -0.42
     ver
    -0.42
     DA
    -0.42
     Lim
    -0.41
     pure
    -0.41
    assadors
    -0.40
    POSITIVE LOGITS
    richTextPanel
    1.02
    GEBURTSDATUM
    0.98
     Roskov
    0.90
     ostavi
    0.86
    ValueStyle
    0.85
    httphttps
    0.83
     resourceCulture
    0.81
    SourceChecksum
    0.81
     myſelf
    0.79
    contentLoaded
    0.79
    Activations Density 0.215%

    No Known Activations