© 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. 1-RES-MATRYOSHKA-DC
    7. 681
    Prev
    Next
    INDEX
    Explanations

    references to specific communication channels or frequencies

    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
     disambiguazione
    -0.85
    AndEndTag
    -0.68
    reportWebVitals
    -0.68
     StatelessWidget
    -0.66
     berätt
    -0.65
     CreateTagHelper
    -0.63
    jsonwebtoken
    -0.61
    
    -0.61
    DockStyle
    -0.60
     مشين
    -0.60
    POSITIVE LOGITS
     channel
    4.56
    channel
    4.19
     Channel
    4.16
     channels
    4.09
    Channel
    3.92
     CHANNEL
    3.81
     Channels
    3.78
    channels
    3.58
    CHANNEL
    3.50
    Channels
    3.36
    Activations Density 0.070%

    No Known Activations