© 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. 16111
    Prev
    Next
    INDEX
    Explanations

    numerical data corresponding to experimental results

    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
    ↵
    -0.57
    r
    -0.46
     New
    -0.45
    full
    -0.45
     values
    -0.45
    .
    -0.44
    <eos>
    -0.43
     r
    -0.42
    cutt
    -0.42
    “
    -0.42
    POSITIVE LOGITS
    OGND
    1.06
     Normdatei
    1.01
    complexContent
    0.98
     للاسماء
    0.97
     autorytatywna
    0.94
    脚注の使い方
    0.88
    HtmlAttribute
    0.87
     صوتيه
    0.86
    \{\\
    0.83
    ScopeManager
    0.82
    Activations Density 0.030%

    No Known Activations