© 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. 11728
    Prev
    Next
    INDEX
    Explanations

    the presence of tunneling interactions in the system

    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
    InputBorder
    -0.68
    Xna
    -0.62
     Pru
    -0.58
     =>
    -0.57
    دانشنامهٔ
    -0.56
     Bris
    -0.55
    ViewImports
    -0.55
    Pru
    -0.52
    Bris
    -0.51
    nomin
    -0.50
    POSITIVE LOGITS
     tunneling
    3.34
     tunne
    2.41
    neling
    1.40
     tunnels
    0.82
    URLException
    0.80
     tunnel
    0.78
    Vidite
    0.77
     Tunnel
    0.74
    tunnel
    0.68
    tun
    0.68
    Activations Density 0.001%

    No Known Activations