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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13787
    Prev
    Next
    INDEX
    Explanations

    references to scientific or technical measurement and modeling processes

    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
    Personendaten
    -1.17
     kasarigan
    -1.12
    StoryboardSegue
    -0.94
    FunctionFlags
    -0.86
    dafx
    -0.86
     Signalez
    -0.85
    InjectAttribute
    -0.81
     @"/
    -0.78
    httphttps
    -0.77
    AndEndTag
    -0.75
    POSITIVE LOGITS
    cti
    3.22
    ctiv
    1.04
    ctif
    0.87
    ctice
    0.81
    ctique
    0.75
    ctico
    0.74
    ctia
    0.71
    ctis
    0.69
    cticas
    0.68
    ctical
    0.66
    Activations Density 0.001%

    No Known Activations