Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 53
    Prev
    Next
    INDEX
    Explanations

    patterns involving mathematical expressions, prime numbers, and computational formulas

    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
    ↵↵
    -0.71
     ſeveral
    -0.68
    <h2>
    -0.65
    ))).
    -0.65
    ...";
    -0.64
    })).
    -0.63
    ])).
    -0.63
    תח
    -0.62
    </h1>
    -0.61
     themſelves
    -0.61
    POSITIVE LOGITS
     p
    1.16
     b
    1.11
     getP
    1.09
     d
    1.05
     m
    1.05
     r
    1.05
     getB
    1.03
    getP
    1.02
    setP
    1.02
     g
    0.97
    Activations Density 12.668%

    No Known Activations