© 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. 0-RES-MATRYOSHKA-DC
    7. 12048
    Prev
    Next
    INDEX
    Explanations

    references to the process of taking things apart or breaking them down

    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
    OGND
    -0.94
     Chriftian
    -0.89
     Diſ
    -0.86
     itſelf
    -0.80
     whoſe
    -0.78
    ſelves
    -0.77
     Efq
    -0.77
     ſeveral
    -0.77
    DockStyle
    -0.76
     myſelf
    -0.75
    POSITIVE LOGITS
     disassemble
    2.63
     disassembled
    2.20
     demolition
    2.05
     disassembly
    1.93
     dismantled
    1.81
     dismantle
    1.77
     demolished
    1.72
     dismantling
    1.66
     demolish
    1.59
     Demolition
    1.57
    Activations Density 0.002%

    No Known Activations