© 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. 3608
    Prev
    Next
    INDEX
    Explanations

    references to the active component of chemical drugs or molecules

    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
     action
    -1.33
    action
    -1.23
    Action
    -1.14
     Action
    -1.11
     actions
    -1.08
     acción
    -1.02
     Actions
    -1.02
     ACTION
    -1.02
    ACTION
    -1.02
    actions
    -0.98
    POSITIVE LOGITS
     active
    3.06
     Active
    2.81
    Active
    2.72
    active
    2.64
     ACTIVE
    2.58
    ACTIVE
    2.23
     aktiven
    2.02
     aktive
    1.97
     activo
    1.96
     attivo
    1.95
    Activations Density 0.035%

    No Known Activations