© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20186
    Prev
    Next
    INDEX
    Explanations

    phrases related to being trapped or burdened by responsibilities or situations

    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
    AddTagHelper
    -0.68
     MediatR
    -0.60
     fehl
    -0.53
    paramref
    -0.52
     dout
    -0.52
    Swish
    -0.52
     Readiness
    -0.51
    ฐ
    -0.51
    UseVisualStyle
    -0.50
     EventEmitter
    -0.50
    POSITIVE LOGITS
    +#+#
    0.71
     gebunden
    0.70
     stuck
    0.67
     Stuck
    0.67
     shackles
    0.65
     constraints
    0.65
     verpflich
    0.63
     bondage
    0.63
     bindings
    0.61
     chained
    0.60
    Activations Density 0.131%

    No Known Activations