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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4651
    Prev
    Next
    INDEX
    Explanations

    the quantity or size-related concepts, particularly references to increase, growth, and measurement contexts

    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
     Original
    -0.48
     старости
    -0.45
    पया
    -0.45
    Original
    -0.45
    راب
    -0.44
     Sens
    -0.43
     tématu
    -0.43
    SM
    -0.43
    iostream
    -0.42
    setHas
    -0.42
    POSITIVE LOGITS
    StoryboardSegue
    0.87
    tanleria
    0.82
    EndContext
    0.82
     EconPapers
    0.81
    AndEndTag
    0.77
     BoxDecoration
    0.75
    CopyWith
    0.75
    onAttach
    0.74
    MemoryWarning
    0.73
    URLException
    0.73
    Activations Density 3.694%

    No Known Activations