© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5852
    Prev
    Next
    INDEX
    Explanations

    alphanumeric strings that resemble hexadecimal color codes or hashes

    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
     disambiguazione
    -1.20
    NameInMap
    -1.00
     Monfieur
    -1.00
     itſelf
    -0.99
    ̓
    -0.94
    mybatisplus
    -0.91
    ंदीखरीदारी
    -0.89
    ^(@)
    -0.89
    NUMX
    -0.88
     IconData
    -0.88
    POSITIVE LOGITS
    ↵↵
    0.71
    <eos>
    0.65
    ↵
    0.59
     .
    0.51
     
    0.44
     t
    0.43
     r
    0.42
     d
    0.42
    dart
    0.41
     f
    0.41
    Activations Density 0.632%

    No Known Activations