© 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. 17067
    Prev
    Next
    INDEX
    Explanations

    references or citations in a document

    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
    All
    -0.53
    Under
    -0.51
    The
    -0.49
    At
    -0.49
    ↵↵
    -0.47
     Under
    -0.47
    dorfer
    -0.47
    -
    -0.47
    O
    -0.47
    E
    -0.47
    POSITIVE LOGITS
    UserScript
    0.85
    ſelf
    0.79
    ſelves
    0.76
    DockStyle
    0.75
    oa̍t
    0.75
     mergeFrom
    0.75
     Forumite
    0.74
     itſelf
    0.71
     Efq
    0.71
     iſt
    0.70
    Activations Density 0.018%

    No Known Activations