© 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. 17552
    Prev
    Next
    INDEX
    Explanations

    references to explosions or explosive events

    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
     rând
    -0.76
     Normdatei
    -0.72
     déchir
    -0.66
     Lari
    -0.64
     chargés
    -0.62
     rê
    -0.61
    vail
    -0.58
     fiebre
    -0.58
     zape
    -0.58
     rêver
    -0.58
    POSITIVE LOGITS
     Explosion
    1.38
     explosion
    1.35
     explosions
    1.35
     exploded
    1.17
     Explo
    1.10
     exploding
    1.06
     explodes
    1.05
     explode
    1.05
     explosives
    1.02
    explosion
    1.01
    Activations Density 0.007%

    No Known Activations