© 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. 28442
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and inquiries related to probability and limits

    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
     performance
    -0.51
     programming
    -0.49
    ]})
    -0.49
    performance
    -0.48
     mengel
    -0.47
     thresholds
    -0.46
    ')")
    -0.46
    "])
    -0.46
    []){
    -0.45
     hierarchy
    -0.45
    POSITIVE LOGITS
    ########.
    0.73
     vertes
    0.65
    SourceChecksum
    0.59
    TagMode
    0.58
    ंदीखरीदारी
    0.56
    UserScript
    0.56
    зулта
    0.56
    Personensuche
    0.55
     GenerationType
    0.54
     Forder
    0.54
    Activations Density 0.180%

    No Known Activations