© 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. 10242
    Prev
    Next
    INDEX
    Explanations

    references to memory and its loss or recovery

    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
    ="#"><
    -0.55
    mybatisplus
    -0.53
     resourceCulture
    -0.52
     Waiting
    -0.52
     clove
    -0.51
     waiting
    -0.51
    ")->
    -0.50
     aufgebaut
    -0.50
     heating
    -0.49
     maneuvers
    -0.49
    POSITIVE LOGITS
    fromnode
    0.75
     random
    0.61
    :✨
    0.60
    AndEndTag
    0.58
     вікі
    0.58
     randomly
    0.56
    random
    0.55
    RegistryLite
    0.55
    protoimpl
    0.54
    摘要
    0.54
    Activations Density 0.139%

    No Known Activations