© 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. 0-RES-MATRYOSHKA-DC
    7. 13220
    Prev
    Next
    INDEX
    Explanations

    references to specific legal or procedural cases

    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
     '\\;'
    -1.08
    ^(@)
    -0.91
     الحره
    -0.86
    Бахар
    -0.82
     nahilalakip
    -0.82
    expandindo
    -0.81
     HasFactory
    -0.80
    tonode
    -0.79
     leaſt
    -0.78
    VERTISEMENT
    -0.77
    POSITIVE LOGITS
     متعلقه
    0.77
     pequeños
    0.49
     porém
    0.47
     unele
    0.47
    us
    0.47
     piccoli
    0.46
    he
    0.46
     pequeñas
    0.46
    <eos>
    0.45
     ciertos
    0.45
    Activations Density 0.017%

    No Known Activations