© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13643
    Prev
    Next
    INDEX
    Explanations

    rotations and transformations expressed with various CSS and SVG syntax

    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
    initializeApp
    -0.71
     dipu
    -0.65
    AndEndTag
    -0.62
    UIControlState
    -0.60
    +#+
    -0.56
    glEnable
    -0.55
    dientemente
    -0.55
    WebpackPlugin
    -0.51
    bootstrapcdn
    -0.50
    Obrázky
    -0.50
    POSITIVE LOGITS
    deg
    2.66
     deg
    1.27
    Deg
    1.07
     Deg
    0.70
    __':
    0.66
    __":
    0.66
    SharedCtor
    0.66
    ValueStyle
    0.60
     <<<<<<<<<<<<<<
    0.59
    zugehen
    0.58
    Activations Density 0.007%

    No Known Activations