© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14960
    Prev
    Next
    INDEX
    Explanations

    references to specific groups or categories in a study

    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
    Negative Logits
    SOUNDBITE
    -0.52
     einerseits
    -0.48
     esist
    -0.48
    過了
    -0.48
    まず
    -0.44
    áva
    -0.44
     primeira
    -0.44
    lahir
    -0.43
    escens
    -0.43
    atmosphère
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    0.83
    GraphicsUnit
    0.81
     fourth
    0.77
    RenderAtEndOf
    0.74
     third
    0.71
     Normdatei
    0.70
    fourth
    0.69
     ostavi
    0.67
     ويكيپيديا
    0.65
     fifth
    0.64
    Activations Density 0.346%

    No Known Activations