© 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. 3-RES-MATRYOSHKA-DC
    7. 2066
    Prev
    Next
    INDEX
    Explanations

    scientific research methodology in biology/chemistry papers

    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
     érde
    -0.51
     vastaan
    -0.49
    といけない
    -0.48
    hmig
    -0.43
    gató
    -0.43
    DAQ
    -0.42
    Portail
    -0.40
    Насе
    -0.40
    gements
    -0.40
     febr
    -0.39
    POSITIVE LOGITS
    fromnode
    0.64
    UnusedPrivate
    0.62
    posedge
    0.61
     Efq
    0.60
     betweenstory
    0.60
     internetowa
    0.60
     magie
    0.59
     coefficients
    0.58
    nvarchar
    0.58
    Cryptography
    0.58
    Activations Density 1.156%

    No Known Activations