© 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. 6670
    Prev
    Next
    INDEX
    Explanations

    code-related tokens or symbols

    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
     __
    -1.32
    ).__
    -1.14
     (__
    -1.11
     pleaſure
    -1.11
    ->__
    -1.08
     greateſt
    -1.05
     anſ
    -1.05
     houſe
    -1.05
     Monfieur
    -1.05
    (__
    -1.04
    POSITIVE LOGITS
    …
    0.58
    .
    0.52
    ↵↵
    0.49
      
    0.48
     B
    0.47
     LayoutInflater
    0.46
    ….
    0.46
    _
    0.45
     there
    0.44
    ...
    0.44
    Activations Density 0.043%

    No Known Activations