© 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. 0-RES-MATRYOSHKA-DC
    7. 11560
    Prev
    Next
    INDEX
    Explanations

    the presence of a guided electromagnetic mode in a waveguide

    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
     Audiodateien
    -0.70
    #![
    -0.69
    UserScript
    -0.59
    WriteBarrier
    -0.59
     Stall
    -0.58
    UITableViewCell
    -0.56
     IEnumerator
    -0.54
    Билгалдахарш
    -0.53
     لدي
    -0.53
     Posi
    -0.53
    POSITIVE LOGITS
     waveguide
    3.11
     refrigerant
    1.91
    ležit
    0.71
    guides
    0.69
     Lightboxes
    0.57
    ivat
    0.56
     Goodwin
    0.56
     صوتيه
    0.56
     Pitman
    0.52
     refriger
    0.51
    Activations Density 0.004%

    No Known Activations