© 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. 6693
    Prev
    Next
    INDEX
    Explanations

    intense or impactful descriptors, particularly focusing on the word "hard" and its variations in context

    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
    LabelTagHelper
    -1.07
     PropTypes
    -1.06
     MonoBehaviour
    -1.03
     propOrder
    -1.00
     numberWith
    -0.98
    SpringBootTest
    -0.96
     Rossetti
    -0.96
    InjectAttribute
    -0.94
    Życiorys
    -0.93
    :✨
    -0.91
    POSITIVE LOGITS
     Hard
    1.23
     HARD
    1.22
    Hard
    1.21
     hard
    1.15
    HARD
    1.09
    hard
    1.05
    硬
    0.97
     Harding
    0.89
    -
    0.87
     hardness
    0.85
    Activations Density 0.034%

    No Known Activations