© 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. 2-RES-MATRYOSHKA-DC
    7. 2805
    Prev
    Next
    INDEX
    Explanations

    specific components or elements related to chambers and chambers' structures

    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
    setVerticalGroup
    -0.75
     sois
    -0.66
     ComVisible
    -0.57
    jooq
    -0.57
    bootstrapcdn
    -0.57
     Saginaw
    -0.56
    addOn
    -0.56
     Pascual
    -0.54
    Rhestr
    -0.53
     Friction
    -0.53
    POSITIVE LOGITS
     chamber
    3.67
     Chamber
    3.30
    chamber
    3.19
     CHAMBER
    3.16
    Chamber
    3.05
     chambers
    3.00
     Chambers
    2.28
    Chambers
    1.94
     Chamberlain
    1.58
    CHAM
    1.52
    Activations Density 0.012%

    No Known Activations