© 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. 7329
    Prev
    Next
    INDEX
    Explanations

    references to Bell Laboratories or Bell systems

    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
     hindurch
    -0.68
     вікі
    -0.68
    skraft
    -0.65
    sslich
    -0.64
    NOPE
    -0.60
    aderie
    -0.59
    woordig
    -0.59
    NameInMap
    -0.58
     habari
    -0.58
     shogun
    -0.58
    POSITIVE LOGITS
     Bel
    2.83
     Bell
    2.81
    Bel
    2.75
    Bell
    2.73
     BELL
    2.73
     bell
    2.67
    bel
    2.61
     BEL
    2.59
    bell
    2.56
     bel
    2.48
    Activations Density 0.018%

    No Known Activations