© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11401
    Prev
    Next
    INDEX
    Explanations

    different types of lines or patterns in data representation

    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
     ddelweddau
    -0.77
     ")");
    -0.73
    InitVars
    -0.72
     Сайт
    -0.71
     postIndex
    -0.69
    intenant
    -0.68
     سكانية
    -0.68
     Moors
    -0.67
    mannschaft
    -0.67
    +};
    -0.66
    POSITIVE LOGITS
    dashed
    0.90
    Dash
    0.84
    dash
    0.78
     dashed
    0.74
     Dash
    0.73
     dash
    0.67
     Das
    0.65
    Das
    0.64
    getMock
    0.64
    InputBorder
    0.63
    Activations Density 0.005%

    No Known Activations