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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14650
    Prev
    Next
    INDEX
    Explanations

    references to detailed descriptions or assessments of molecular, biological, or structural characteristics

    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
    достатки
    -0.55
    rdp
    -0.55
    '$
    -0.54
     appearing
    -0.52
     appear
    -0.51
    iniums
    -0.51
    tuje
    -0.50
    kuuta
    -0.50
    RIF
    -0.49
     ↓,
    -0.49
    POSITIVE LOGITS
    BeginInit
    0.79
    хьтан
    0.74
    ագրություններ
    0.72
    ValueStyle
    0.70
     AssemblyCompany
    0.69
    Characterization
    0.69
    BASEPATH
    0.68
     ProtoMessage
    0.65
     esternos
    0.65
    RenderAtEndOf
    0.63
    Activations Density 0.004%

    No Known Activations