© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15380
    Prev
    Next
    INDEX
    Explanations

    references to reinforcement of materials or concepts

    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
     defended
    -0.84
     defend
    -0.69
    \{\\
    -0.68
    ArgsConstructor
    -0.66
     defends
    -0.66
     المعيارى
    -0.65
     defending
    -0.64
    存于互联网档案馆
    -0.63
      (
    -0.61
     betweenstory
    -0.59
    POSITIVE LOGITS
     reinforcement
    2.73
     Reinforcement
    2.48
     reinforcing
    2.13
     reinforcements
    2.03
     reinforce
    2.02
    forcement
    1.84
    Rein
    1.65
    rein
    1.60
     reinforced
    1.52
    reinforced
    1.47
    Activations Density 0.001%

    No Known Activations