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. 15744
    Prev
    Next
    INDEX
    Explanations

    specific names of authors and directors in a film or literary context

    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
     kasarigan
    -0.99
     EconPapers
    -0.96
     itſelf
    -0.88
     Мексичка
    -0.86
    IntoConstraints
    -0.85
    ValueStyle
    -0.82
    ViewImports
    -0.77
    CloseOperation
    -0.77
    principalColumn
    -0.74
     ligiloj
    -0.74
    POSITIVE LOGITS
     d
    0.48
     (
    0.43
    олові
    0.43
     n
    0.41
    디어
    0.41
     presentation
    0.40
    那里
    0.40
     
    0.40
     o
    0.39
    Abstract
    0.38
    Activations Density 0.234%

    No Known Activations