© 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. 11343
    Prev
    Next
    INDEX
    Explanations

    references to academic citations or authors in scientific literature

    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
    (!__
    -0.69
     resourceCulture
    -0.67
    orsese
    -0.63
     cava
    -0.63
    featureID
    -0.62
    ,-.
    -0.62
    ----</
    -0.61
     itſelf
    -0.60
    transQ
    -0.59
    Хьажоргаш
    -0.59
    POSITIVE LOGITS
    DataSnapshot
    0.62
    évaluateur
    0.59
    InSection
    0.50
     Saltar
    0.49
    ]")]
    0.48
    makeConstraints
    0.47
     Assisi
    0.47
    Оп
    0.47
    ngdoc
    0.45
     quoi
    0.45
    Activations Density 0.026%

    No Known Activations