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. 8888
    Prev
    Next
    INDEX
    Explanations

    numerical values represented by symbols used in mathematical equations or expressions

    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
    Enllaços
    -0.84
     Northampton
    -0.84
    ampton
    -0.84
    Zeneca
    -0.83
     productName
    -0.83
     CTP
    -0.82
     pleaſure
    -0.81
     Sunlight
    -0.81
    gdx
    -0.80
     suns
    -0.79
    POSITIVE LOGITS
    ell
    1.20
     Kell
    0.94
    ℓ
    0.92
     ell
    0.92
     Ell
    0.91
    Ell
    0.91
    ELL
    0.82
     ELL
    0.78
     Pell
    0.76
     });
    
    0.71
    Activations Density 0.024%

    No Known Activations