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. 6288
    Prev
    Next
    INDEX
    Explanations

    mathematical or graphical representations of curves

    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
     ){
    
    -0.77
    ":
    
    -0.74
     CommonModule
    -0.74
    IContainer
    -0.71
    epam
    -0.71
    Diwedd
    -0.71
    Aidan
    -0.69
    SL
    -0.67
    ++
    
    -0.66
    antaranya
    -0.65
    POSITIVE LOGITS
     Curves
    1.56
    curves
    1.45
    Curves
    1.44
    curve
    1.41
     curves
    1.37
     Curve
    1.34
    Curve
    1.30
     CUR
    1.26
    CUR
    1.25
     curve
    1.24
    Activations Density 0.094%

    No Known Activations