© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 482
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and their findings

    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
    webElementXpaths
    -0.88
    AutoScaleMode
    -0.76
    aarrggbb
    -0.73
    Билгалдахарш
    -0.71
     BoxDecoration
    -0.69
    PropertyChanging
    -0.68
     GenerationType
    -0.66
    WebElementEntity
    -0.66
     المعيارى
    -0.66
    esomeness
    -0.66
    POSITIVE LOGITS
    agré
    0.46
     Abonnez
    0.45
    pov
    0.44
    esModule
    0.44
    vece
    0.43
    flashdata
    0.43
    λέ
    0.42
    ,
    0.41
    Yet
    0.41
    いますが
    0.41
    Activations Density 1.509%

    No Known Activations