© 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. 11356
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or significant data points in a document

    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
     or
    -0.46
     inc
    -0.40
    رائ
    -0.39
    ney
    -0.39
     Dic
    -0.38
    (/[
    -0.38
     le
    -0.38
    leigh
    -0.38
    IST
    -0.37
     νο
    -0.37
    POSITIVE LOGITS
     kasarigan
    0.82
    httphttps
    0.75
     Universitaria
    0.75
    sidemargin
    0.74
    Espèce
    0.72
    mybatisplus
    0.72
    oredCriteria
    0.72
    $_['
    0.71
    ArrowToggle
    0.71
     sagrada
    0.71
    Activations Density 0.010%

    No Known Activations