© 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. 3328
    Prev
    Next
    INDEX
    Explanations

    specific keywords and terms used in scientific and technical contexts

    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
     ability
    -0.53
    ism
    -0.52
    =?";
    -0.48
     StatelessWidget
    -0.47
    ffion
    -0.47
     Colonna
    -0.47
    withId
    -0.47
    IMPORTED
    -0.46
    IDAS
    -0.46
    ogan
    -0.46
    POSITIVE LOGITS
    AnchorStyles
    0.74
    DeleteBehavior
    0.63
     kasarigan
    0.59
    Бахар
    0.57
     Meksiku
    0.57
    GeneratedCode
    0.54
    InitVars
    0.53
     चीज़ों
    0.53
    InvalidProtocol
    0.52
    énario
    0.52
    Activations Density 0.286%

    No Known Activations