© 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. 15369
    Prev
    Next
    INDEX
    Explanations

    geometric arrangements and configurations involving projective and affine spaces

    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
     متعلقه
    -0.76
    +#+#
    -0.58
    IUrlHelper
    -0.58
    Nationalité
    -0.57
     للمعارف
    -0.54
    Personensuche
    -0.53
    mány
    -0.53
    TagMode
    -0.52
    واره
    -0.50
    rium
    -0.49
    POSITIVE LOGITS
     projective
    3.61
     proyec
    0.82
     affine
    0.73
    tanleria
    0.67
    ContextHolder
    0.63
    ագրություններ
    0.60
    UnusedPrivate
    0.58
    tahui
    0.57
    jective
    0.57
    ribune
    0.53
    Activations Density 0.001%

    No Known Activations