© 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. 299
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical models and healthcare safety assessments

    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
     defaultstate
    -1.02
    aarrggbb
    -0.97
    دانشنامهٔ
    -0.97
    تقاوى
    -0.96
    AddTagHelper
    -0.94
    liothèque
    -0.85
    bootstrapcdn
    -0.85
     ***!
    -0.85
    tagHelperRunner
    -0.84
     useRouter
    -0.81
    POSITIVE LOGITS
     jellemző
    0.69
     feroit
    0.66
     pouvoit
    0.63
     vectoriales
    0.62
    팎
    0.62
    WC
    0.60
     humains
    0.60
     vlak
    0.59
    baliknya
    0.59
     vektör
    0.58
    Activations Density 3.742%

    No Known Activations