© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5602
    Prev
    Next
    INDEX
    Explanations

    discussions related to financial implications and health insurance topics

    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
    adaptiveStyles
    -0.73
    }))
    -0.67
    createCanvas
    -0.66
    PyExc
    -0.66
    queryInterface
    -0.66
    ʺ
    -0.65
     Wicidata
    -0.64
    SuspendLayout
    -0.63
    RegistryLite
    -0.63
    complexContent
    -0.62
    POSITIVE LOGITS
     still
    0.80
    still
    0.75
    Still
    0.68
     Still
    0.62
    仍然
    0.58
    仍
    0.58
     tetap
    0.57
    依然
    0.57
     vẫn
    0.57
    STILL
    0.56
    Activations Density 0.291%

    No Known Activations