© 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. 5277
    Prev
    Next
    INDEX
    Explanations

    technical specifications and performance details related to device circuitry

    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
    ]--;
    -0.84
    ieteur
    -0.82
    ductory
    -0.76
    InputBorder
    -0.76
    NUMX
    -0.75
    SPATH
    -0.72
    xically
    -0.72
    --){
    -0.71
    )++;
    -0.71
    resizingMask
    -0.71
    POSITIVE LOGITS
    #
    0.67
    he
    0.55
    addCriterion
    0.53
    mine
    0.52
    ，
    0.51
     Besides
    0.51
    、
    0.51
    ：
    0.50
     especial
    0.49
    Abp
    0.49
    Activations Density 2.042%

    No Known Activations