© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13978
    Prev
    Next
    INDEX
    Explanations

    references to the range of values or measurements typically associated with scientific or technical data

    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
     AssemblyCulture
    -0.63
     utafitiHapana
    -0.57
    casian
    -0.57
    Pvt
    -0.55
     communication
    -0.54
    qvarna
    -0.52
    CloseHandle
    -0.52
     jScrollPane
    -0.52
     correspondence
    -0.51
    FirstResponder
    -0.51
    POSITIVE LOGITS
     विश्वसनीयता
    0.60
    rawDesc
    0.59
    Portail
    0.56
     variety
    0.56
     lot
    0.55
     ostavi
    0.54
    出版年
    0.53
     indisponible
    0.53
    Autoritní
    0.52
    場合があります
    0.52
    Activations Density 0.013%

    No Known Activations