© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16601
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to explosive devices or bombs

    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
     brevis
    -0.71
    vereign
    -0.62
    zelfde
    -0.59
    Cringe
    -0.58
    Види
    -0.56
     twar
    -0.55
     métiers
    -0.54
     zewnętrzne
    -0.52
    Behaviors
    -0.52
    Subjects
    -0.51
    POSITIVE LOGITS
     bomb
    2.02
     BOMB
    1.84
    Bomb
    1.83
     Bomb
    1.82
     bombs
    1.79
    bomb
    1.77
     Bombs
    1.74
     bombing
    1.68
     bombed
    1.63
    bombs
    1.54
    Activations Density 0.004%

    No Known Activations