© 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. 2718
    Prev
    Next
    INDEX
    Explanations

    instances of one thing in relation to another.

    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
    htdocs
    -0.65
     respecte
    -0.59
    Manbalar
    -0.59
     lenker
    -0.57
     متعلقه
    -0.57
     Chwiliwch
    -0.57
    aard
    -0.56
    ScopeManager
    -0.56
    cplusplus
    -0.56
     relativi
    -0.56
    POSITIVE LOGITS
    brainly
    0.66
     للمعارف
    0.62
    andaş
    0.57
    期刊论文
    0.57
    Pooling
    0.55
    LoadScene
    0.55
    ])):
    0.53
     that
    0.52
    ))/(
    0.52
     aqueles
    0.52
    Activations Density 0.381%

    No Known Activations