© 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. 11973
    Prev
    Next
    INDEX
    Explanations

    references to specific spatial locations in a text or scene

    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
    انگلیسی
    -0.60
     kaarangay
    -0.59
    homonymie
    -0.58
     ProtoMessage
    -0.56
    setVerticalGroup
    -0.56
     beginnetje
    -0.55
     ujednoznacz
    -0.55
     lèvres
    -0.54
     héri
    -0.54
    expandindo
    -0.52
    POSITIVE LOGITS
    hline
    0.66
     ↑
    0.64
    MENAFN
    0.60
    ագրություններ
    0.53
    ]?
    0.52
    thâu
    0.52
    ?".
    0.52
    wis
    0.52
    ?]
    0.50
    crollView
    0.50
    Activations Density 0.146%

    No Known Activations