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. 14574
    Prev
    Next
    INDEX
    Explanations

    references to a specific author or researcher

    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
    +#+#
    -0.84
     MonoBehaviour
    -0.82
    nestjs
    -0.77
     ModelExpression
    -0.71
    UrlResolution
    -0.70
     PyObject
    -0.69
     TextInputType
    -0.68
    protoimpl
    -0.65
     BoxFit
    -0.63
    tagHelperRunner
    -0.63
    POSITIVE LOGITS
    isu
    1.63
     Bert
    1.55
    isy
    1.52
    Bert
    1.35
    usal
    0.95
     Bing
    0.71
    ISY
    0.60
     bert
    0.60
    Bing
    0.50
    endy
    0.50
    Activations Density 0.001%

    No Known Activations