© 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. 9593
    Prev
    Next
    INDEX
    Explanations

    terms related to sustainability and sustained actions or conditions

    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
     Henson
    -0.94
     وتسجيلات
    -0.87
    PhysRev
    -0.85
    μο
    -0.80
     propOrder
    -0.78
    انجليز
    -0.75
     Childs
    -0.75
     Pryor
    -0.75
    ikistan
    -0.75
    cestry
    -0.75
    POSITIVE LOGITS
     Sust
    1.20
     Sustain
    1.19
    Sustain
    1.09
    sustain
    1.05
    sust
    0.99
     sustain
    0.98
     SUSTAIN
    0.97
     sustains
    0.93
    USTAIN
    0.90
     Sosten
    0.86
    Activations Density 0.007%

    No Known Activations