© 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. 10716
    Prev
    Next
    INDEX
    Explanations

    technical terms related to heat transfer and cooling systems

    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
     snippetHide
    -0.56
    ]")]
    -0.56
    addCriterion
    -0.55
    OnAdd
    -0.52
    yntaxException
    -0.50
    webElement
    -0.49
     Echo
    -0.48
    orea
    -0.47
    술
    -0.47
    stdc
    -0.45
    POSITIVE LOGITS
     MainAxisSize
    0.70
     coolant
    0.69
     cooling
    0.69
     Cooling
    0.69
    numerusform
    0.69
    cooling
    0.67
     Kühl
    0.67
     exchanger
    0.65
    ChildScrollView
    0.65
     radiator
    0.64
    Activations Density 0.020%

    No Known Activations