© 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. 21194
    Prev
    Next
    INDEX
    Explanations

    expressions related to worry and anxiety

    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
    principalColumn
    -0.89
    ReusableCell
    -0.88
    ContentAlignment
    -0.83
     Celeste
    -0.77
    memberof
    -0.73
    SceneManagement
    -0.71
    UpInside
    -0.69
     Steen
    -0.68
    substack
    -0.68
    mace
    -0.68
    POSITIVE LOGITS
     Worry
    1.26
    worry
    1.15
     worry
    1.07
     worries
    1.03
     Sorgen
    0.85
    orry
    0.77
     worrying
    0.76
     worried
    0.73
    ]();
    0.72
    talk
    0.69
    Activations Density 0.004%

    No Known Activations