© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13903
    Prev
    Next
    INDEX
    Explanations

    snippets of code containing class definitions and associated method structures

    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
     femininas
    -0.60
    jsonwebtoken
    -0.59
     skimage
    -0.59
    tagHelperRunner
    -0.56
    trends
    -0.54
    onActivityResult
    -0.54
    getAction
    -0.53
    Più
    -0.52
    attendre
    -0.52
     consultato
    -0.51
    POSITIVE LOGITS
    classes
    2.08
     Réponses
    0.73
     noDo
    0.60
    nino
    0.58
    himu
    0.56
     release
    0.56
    ekš
    0.55
    انيف
    0.54
    types
    0.54
    epiece
    0.54
    Activations Density 0.001%

    No Known Activations