© 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. 10528
    Prev
    Next
    INDEX
    Explanations

    terms related to "drift" in various contexts

    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
    +#+
    -0.79
    expandindo
    -0.73
     fatica
    -0.72
    SuppressMessage
    -0.70
     Meksiku
    -0.70
     emperors
    -0.70
    Fontes
    -0.69
     insulators
    -0.69
     Brakes
    -0.69
    المشاركات
    -0.68
    POSITIVE LOGITS
     drift
    1.63
     drifting
    1.50
    drift
    1.48
    Drift
    1.46
     Drift
    1.44
     drifted
    1.34
     drifts
    1.24
     floating
    1.17
     Floating
    1.15
     floated
    1.13
    Activations Density 0.013%

    No Known Activations