© 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. 14688
    Prev
    Next
    INDEX
    Explanations

    instances of irony and related concepts

    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
    RenderAtEndOf
    -0.85
     NSCoder
    -0.82
    DeleteBehavior
    -0.73
    Хьажоргаш
    -0.65
     متعلقه
    -0.65
    URLException
    -0.62
    NOPQRST
    -0.59
     extraordinary
    -0.56
    unhofer
    -0.56
    intios
    -0.55
    POSITIVE LOGITS
     irony
    0.98
     ironic
    0.98
     ironically
    0.82
    Ironically
    0.76
     Ironically
    0.72
    ironically
    0.68
     hedges
    0.61
    StateList
    0.59
     paradox
    0.58
     Paradox
    0.56
    Activations Density 0.027%

    No Known Activations