© 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. 10834
    Prev
    Next
    INDEX
    Explanations

    references to specific technical components related to fire containment, particularly flanking regions and inverter units

    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
     Gautier
    -0.61
     typelib
    -0.58
     насељу
    -0.56
     للمعارف
    -0.55
    ыгана
    -0.55
    揄
    -0.55
     uska
    -0.54
     looser
    -0.54
    GoogleMap
    -0.52
    Polizei
    -0.51
    POSITIVE LOGITS
     AppCompat
    0.77
    uxxxx
    0.66
    ({},
    0.64
    jetbrains
    0.63
    addLast
    0.63
    plo
    0.60
    Atoi
    0.58
    +#+#
    0.58
    xtext
    0.57
     axle
    0.56
    Activations Density 0.119%

    No Known Activations