© 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. 15455
    Prev
    Next
    INDEX
    Explanations

    references to specific chemical agents or measurements used in scientific contexts

    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
     BALL
    -0.58
     Ball
    -0.54
    Ball
    -0.53
     limão
    -0.53
     mentale
    -0.52
    mặt
    -0.51
     flocc
    -0.51
    ArgsConstructor
    -0.49
    ulihan
    -0.49
     propOrder
    -0.49
    POSITIVE LOGITS
    AQ
    3.47
     AQ
    2.38
    aq
    1.57
     aq
    1.31
    Aq
    1.00
     Aq
    0.88
    ⓧ
    0.80
    adaptiveStyles
    0.79
    +:+
    0.70
     AssemblyCulture
    0.68
    Activations Density 0.001%

    No Known Activations