© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4726
    Prev
    Next
    INDEX
    Explanations

    mentions of specific technical codes, identifiers, or specialized terminology typically associated with scientific or medical 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
     للمعارف
    -0.91
    tvguidetime
    -0.82
     يتيمه
    -0.79
     nahilalakip
    -0.77
    expandindo
    -0.75
    Personensuche
    -0.73
     utafitiHapana
    -0.70
     snippetHide
    -0.69
    });
    -0.62
     ModelExpression
    -0.60
    POSITIVE LOGITS
    öhnen
    0.45
     Tuf
    0.44
     Jerusal
    0.44
    Spacer
    0.43
     Connectez
    0.43
    stringstream
    0.42
    WireFormatLite
    0.42
     ahu
    0.42
     Herrick
    0.42
    ;++
    0.42
    Activations Density 0.831%

    No Known Activations