© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4656
    Prev
    Next
    INDEX
    Explanations

    references to mechanical lifts or lifting mechanisms

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.75
     MainAxisSize
    -0.70
    íslu
    -0.69
     jspb
    -0.66
     geox
    -0.66
    UnifiedTopology
    -0.66
    Calais
    -0.65
     Baillargeon
    -0.64
    qiu
    -0.63
     Wiktionnaire
    -0.63
    POSITIVE LOGITS
     lift
    3.59
     Lift
    3.36
     lifts
    3.23
    lift
    3.14
    Lift
    3.13
     lifting
    2.94
     lifted
    2.86
     LIFT
    2.86
    lifts
    2.75
     Lifting
    2.58
    Activations Density 0.015%

    No Known Activations