© 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. 4739
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a shift away from previous states or beliefs

    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
    Personendaten
    -0.92
     Wiktionnaire
    -0.77
    kloped
    -0.77
     AssemblyCulture
    -0.73
     intptr
    -0.73
     ویکی‌پدیا
    -0.71
    󠁿
    -0.70
     متعلقه
    -0.69
     Himo
    -0.67
     ujednoznacz
    -0.66
    POSITIVE LOGITS
    不再
    0.81
     longer
    0.62
    longer
    0.61
     Теперь
    0.60
     ceased
    0.58
     artık
    0.58
     luster
    0.57
     anymore
    0.56
    もはや
    0.56
     Longer
    0.56
    Activations Density 0.256%

    No Known Activations