Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 17739
    Prev
    Next
    INDEX
    Explanations

    conditional phrases indicating potential outcomes or possibilities

    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
     initComponents
    -0.82
    yntaxException
    -0.74
    SpringBootTest
    -0.72
     المعيارى
    -0.72
     Majefty
    -0.72
     reaſon
    -0.68
    rizona
    -0.68
     Jefus
    -0.68
     itſelf
    -0.67
    
    -0.67
    POSITIVE LOGITS
    FieldBuilder
    0.72
    ImageContext
    0.71
    Specifiche
    0.54
    المناصب
    0.54
    createServer
    0.53
     AssemblyVersion
    0.50
    uevas
    0.50
    ppes
    0.50
    sendLogPayload
    0.48
    WriteBarrier
    0.48
    Activations Density 0.059%

    No Known Activations