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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26481
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and semicolons

    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
    "])
    -0.56
    鰭
    -0.54
    ='';
    -0.54
    ]();
    -0.50
    ="">
    -0.48
    années
    -0.48
    "]);
    -0.48
    =""/>
    -0.47
    ibly
    -0.47
    "]="
    -0.47
    POSITIVE LOGITS
     continúas
    0.88
    ⓧ
    0.82
    twimg
    0.80
     SqlCommand
    0.78
     CreateTagHelper
    0.77
    存于互联网档案馆
    0.77
    RuleContext
    0.75
     kasarigan
    0.74
     nahilalakip
    0.74
    prnewswire
    0.73
    Activations Density 0.007%

    No Known Activations