© 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. 301
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

    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
     tartalomajánló
    -0.97
    ]")]
    -0.91
    .*")]
    -0.91
     дописавши
    -0.85
    Hentet
    -0.84
    )))),
    -0.83
    styleType
    -0.79
    انيف
    -0.76
    @[+][
    -0.75
     مشين
    -0.75
    POSITIVE LOGITS
    </strong>
    0.68
    中略
    0.64
    </em>
    0.62
    </u>
    0.60
    </b>
    0.56
    </h2>
    0.55
    hauer
    0.55
    UserScript
    0.54
    0.53
    ant
    0.52
    Activations Density 5.341%
    No Known Activations