© 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. 229
    Prev
    Next
    INDEX
    Explanations

    detailed references to articles or narratives

    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
    cstdlib
    -0.73
    herokuapp
    -0.68
    interopRequire
    -0.66
    Laughs
    -0.65
    kfree
    -0.63
     resourceCulture
    -0.63
    LikeLike
    -0.62
    stdlib
    -0.62
     通販
    -0.61
    providedIn
    -0.60
    POSITIVE LOGITS
     text
    0.93
     texts
    0.88
     narration
    0.85
     about
    0.84
     written
    0.83
     aloud
    0.82
     stories
    0.81
     statements
    0.81
     telling
    0.81
     narrated
    0.80
    Activations Density 5.288%

    No Known Activations