© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 680
    Prev
    Next
    INDEX
    Explanations

    the word "address"

    oai_token-act-pair · gemini-2.0-flash
    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
    ఔ
    -0.71
     AUS
    -0.63
    DNEY
    -0.60
    asius
    -0.59
     reten
    -0.58
     Fland
    -0.56
    tale
    -0.56
    Anja
    -0.56
     equivalent
    -0.55
    Acro
    -0.55
    POSITIVE LOGITS
     address
    3.11
     ADDRESS
    3.02
     Address
    3.00
    address
    2.97
     addresses
    2.92
     Addresses
    2.84
    Address
    2.80
     addressed
    2.64
    ADDRESS
    2.64
     addressing
    2.58
    Activations Density 0.159%

    No Known Activations