© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6737
    Prev
    Next
    INDEX
    Explanations

    references to audio/video or multimedia format identifiers

    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
    AddTagHelper
    -0.69
     betweenstory
    -0.69
    
    -0.66
    cshtml
    -0.65
    tonsoft
    -0.64
     Sze
    -0.64
    bootstrapcdn
    -0.63
     resourceCulture
    -0.63
     صوتيه
    -0.62
    Sze
    -0.62
    POSITIVE LOGITS
    av
    3.34
     av
    2.83
    AV
    2.80
     Av
    2.48
     AV
    2.47
    Av
    2.47
    avs
    1.77
    ave
    1.68
    ava
    1.59
    avi
    1.54
    Activations Density 0.067%

    No Known Activations