© 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. 3139
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to technology, specifically programming and data structures

    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
    ness
    -1.16
    n
    -1.02
    d
    -0.98
    r
    -0.83
    nya
    -0.75
    ship
    -0.73
    rd
    -0.72
    н
    -0.71
    了
    -0.69
    s
    -0.68
    POSITIVE LOGITS
    e
    1.11
     CIE
    1.07
     CME
    1.06
     SSE
    1.04
    eeeeeeee
    1.04
    Mane
    1.02
     CPE
    1.01
     DCE
    1.01
     XE
    1.00
     CTE
    1.00
    Activations Density 2.035%

    No Known Activations