© 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. 18882
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and qualifiers indicating uncertainty or improbability

    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
     protoimpl
    -1.05
    protoimpl
    -0.84
    })));
    -0.82
     AssemblyCompany
    -0.81
     Италијани
    -0.79
    хьтан
    -0.76
     CanadaChoose
    -0.74
     Савезне
    -0.74
     <=",
    -0.74
    AndEndTag
    -0.74
    POSITIVE LOGITS
     progress
    0.47
    świ
    0.46
    PROGRESS
    0.44
     Verhält
    0.43
    ệu
    0.43
    urlpatterns
    0.42
    aspectRatio
    0.41
    NSIndexPath
    0.41
    progress
    0.40
     Might
    0.39
    Activations Density 0.082%

    No Known Activations