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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13421
    Prev
    Next
    INDEX
    Explanations

    references to names of specific, numbered, or titled special series, arrangements, or versions

    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
     raiſ
    -0.82
     houſe
    -0.80
     Houſe
    -0.78
     Anſ
    -0.73
     ſever
    -0.70
     cauſe
    -0.69
    ngdoc
    -0.69
     ſtate
    -0.68
     kiệm
    -0.68
     ſche
    -0.68
    POSITIVE LOGITS
     Ten
    2.17
    Ten
    1.75
     TEN
    0.75
    endphp
    0.63
    }`;
    0.55
    ijin
    0.52
    sidemargin
    0.52
     Ta
    0.52
    addComponent
    0.49
    kkelen
    0.49
    Activations Density 0.002%

    No Known Activations