© 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. 30712
    Prev
    Next
    INDEX
    Explanations

    References to deterioration or decline

    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
    
    -0.82
    DockStyle
    -0.73
    ثيق
    -0.68
    EndContext
    -0.66
    XmlAccessType
    -0.66
    BagLayout
    -0.66
    webElement
    -0.65
    awtextra
    -0.64
    __*/
    -0.64
    MotionEvent
    -0.63
    POSITIVE LOGITS
     decayed
    0.88
     dilapidated
    0.86
     decaying
    0.85
     decay
    0.84
     deteriorated
    0.80
     Decay
    0.78
    Decay
    0.73
     crumbling
    0.72
     decays
    0.69
     tattered
    0.67
    Activations Density 0.139%

    No Known Activations