© 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. 3-RES-MATRYOSHKA-DC
    7. 2901
    Prev
    Next
    INDEX
    Explanations

    HTML code

    oai_token-act-pair · gemini-2.0-flash
    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
      
    -0.59
     str
    -0.53
     home
    -0.50
    AutoField
    -0.50
    <eos>
    -0.49
     noten
    -0.47
     sil
    -0.44
     חיצוניים
    -0.44
     to
    -0.43
    郎
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.99
    bootstrapcdn
    0.94
     Efq
    0.89
     Spaniards
    0.88
    AddHtmlAttribute
    0.87
    AndEndTag
    0.85
     $_"
    0.85
     ComVisible
    0.83
    NamedQueries
    0.83
     scaricare
    0.83
    Activations Density 0.131%

    No Known Activations