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. 9-RES-MATRYOSHKA-DC
    4. 16687
    Prev
    Next
    INDEX
    Explanations

    file paths

    oai_token-act-pair · gemini-2.0-flash
    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
     purpoſe
    -0.84
     protoimpl
    -0.77
    nocache
    -0.72
     ſen
    -0.71
    usercontent
    -0.70
    ThroughAttribute
    -0.70
     houſe
    -0.70
    رشف
    -0.69
     pleaſure
    -0.69
     NavController
    -0.68
    POSITIVE LOGITS
    <bos>
    0.63
     *)__
    0.49
     Mr
    0.48
    __':
    
    0.48
    __':
    0.47
    loed
    0.47
     }^{
    0.47
    </b>
    0.47
    </sub>
    0.46
    bringt
    0.46
    Activations Density 0.002%

    No Known Activations