© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6106
    Prev
    Next
    INDEX
    Explanations

    frequent symbols related to formatting or citation markers 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
    Negative Logits
    stums
    -0.86
    pausal
    -0.82
     secas
    -0.80
     idéia
    -0.79
     mijne
    -0.78
     démocr
    -0.77
    pośred
    -0.77
    henge
    -0.77
    otene
    -0.75
     métallique
    -0.75
    POSITIVE LOGITS
    \]
    1.45
    }\]
    1.10
     \]
    0.96
    filepath
    0.75
     Cromwell
    0.68
     clazz
    0.68
     Cir
    0.67
    ]--;
    0.63
    </s>
    0.61
    )])
    0.61
    Activations Density 0.225%

    No Known Activations