© 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. 3481
    Prev
    Next
    INDEX
    Explanations

    references to structural failures or destructive events, particularly explosions

    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
    لاعب
    -0.62
     coper
    -0.58
     Wex
    -0.51
     Cane
    -0.50
    phene
    -0.50
     Hoe
    -0.50
     Heal
    -0.50
     betweenstory
    -0.50
     Motta
    -0.49
    Cerv
    -0.49
    POSITIVE LOGITS
     explosion
    2.55
     blast
    2.52
     bomb
    2.38
     Explosion
    2.38
     explosions
    2.33
     Blast
    2.28
     blasts
    2.22
     Bomb
    2.17
    blast
    2.16
     bombs
    2.14
    Activations Density 0.103%

    No Known Activations