© 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. 11041
    Prev
    Next
    INDEX
    Explanations

    phrases related to genetic mutations and their implications

    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
    клопе
    -0.84
    verwijspagina
    -0.75
    WebServlet
    -0.74
     ujednoznacz
    -0.73
     intptr
    -0.70
    Enllaces
    -0.70
     ModelExpression
    -0.69
    Portály
    -0.69
     <=",
    -0.65
     Theſe
    -0.65
    POSITIVE LOGITS
     herself
    0.49
    let
    0.46
     للمعارف
    0.46
     himself
    0.46
    clientY
    0.46
    Composable
    0.43
     ourselves
    0.40
    StackNavigator
    0.40
    AdapterFactory
    0.40
    っくり
    0.40
    Activations Density 0.271%

    No Known Activations