© 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. 19883
    Prev
    Next
    INDEX
    Explanations

    words related to discussions and acknowledgments in research contexts

    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
    väl
    -0.63
    må
    -0.58
     féminine
    -0.55
     parete
    -0.53
     littéraire
    -0.52
     remarquer
    -0.52
     szép
    -0.52
     creativos
    -0.52
     övers
    -0.52
     digitais
    -0.52
    POSITIVE LOGITS
    matchCondition
    0.63
    CPtr
    0.62
    ագրություններ
    0.62
    曖昧さ回避
    0.61
    ThroughAttribute
    0.60
    UnitTesting
    0.60
    urlpatterns
    0.59
    mybatisplus
    0.59
    허
    0.59
    KommentareTeilen
    0.56
    Activations Density 0.008%

    No Known Activations