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. 15341
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the existence or condition of something

    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
    ChildScrollView
    -0.89
    '}>
    -0.85
     autorytatywna
    -0.84
     المعيارى
    -0.82
    OGND
    -0.81
    InjectAttribute
    -0.80
    )");
    
    -0.79
    "}>
    -0.77
    HasForeignKey
    -0.76
    )')
    -0.75
    POSITIVE LOGITS
    ToTensor
    0.44
     dần
    0.43
     Roman
    0.43
    Roman
    0.42
     mää
    0.41
     Sentences
    0.40
    output
    0.39
    wiat
    0.39
     Facultad
    0.39
    noun
    0.39
    Activations Density 0.003%

    No Known Activations