© 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. 12-RES-MATRYOSHKA-DC
    7. 14094
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of 'burning' and its effects

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.75
     Farb
    -0.74
    벤트
    -0.74
    stateProvider
    -0.71
    ไซ
    -0.68
    ade
    -0.66
    tabular
    -0.64
    adec
    -0.63
     apă
    -0.63
     fapt
    -0.63
    POSITIVE LOGITS
     Burns
    1.39
     burns
    1.36
     burn
    1.35
     BURN
    1.34
     Burning
    1.29
    burns
    1.27
     Burn
    1.26
     burned
    1.23
     burning
    1.22
    Burns
    1.20
    Activations Density 0.008%

    No Known Activations