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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14572
    Prev
    Next
    INDEX
    Explanations

    instructions related to removing or deleting items

    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
    ди
    -0.48
    ങ്ക
    -0.45
    zydent
    -0.43
    whal
    -0.43
     situ
    -0.42
    ed
    -0.41
    提
    -0.41
     body
    -0.41
     me
    -0.40
     He
    -0.40
    POSITIVE LOGITS
    expandindo
    0.98
     Deletion
    0.91
     deletion
    0.88
    WEBPACK
    0.88
    ValueStyle
    0.86
    Бахар
    0.84
    mybatisplus
    0.82
    Източници
    0.81
    +#+
    0.80
    Deletion
    0.79
    Activations Density 0.011%

    No Known Activations