© 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. 10750
    Prev
    Next
    INDEX
    Explanations

    negations and words related to the lack of ability or responsibility

    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
    ьажоргаш
    -0.57
    帖最后由
    -0.57
     circonst
    -0.55
    tagHelperRunner
    -0.53
     hausse
    -0.52
     potreb
    -0.51
     juſt
    -0.51
    berdayakan
    -0.50
     cât
    -0.50
     république
    -0.50
    POSITIVE LOGITS
    vably
    0.61
    Diwedd
    0.61
    mtrl
    0.60
     ơn
    0.57
    WriteBarrier
    0.56
     activado
    0.54
    çade
    0.53
    ()][
    0.53
    ],
    0.52
    Бахар
    0.52
    Activations Density 0.122%

    No Known Activations