© 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. 26803
    Prev
    Next
    INDEX
    Explanations

    instances of specific formatting or syntax errors in text

    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
    ReadKey
    -0.52
    idit
    -0.50
     []:
    -0.47
    SIMPLE
    -0.46
    abal
    -0.46
    urra
    -0.45
    цезда
    -0.42
    jss
    -0.42
     simple
    -0.42
    CrossRef
    -0.42
    POSITIVE LOGITS
    تقاوى
    1.05
    Geplaatst
    0.91
    oredCriteria
    0.79
     nahilalakip
    0.76
     Exactos
    0.75
    Искәрмәләр
    0.74
     kasarigan
    0.73
     Roskov
    0.72
     transfieras
    0.72
     Italijanski
    0.71
    Activations Density 0.000%

    No Known Activations