© 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. 1770
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     
    -0.65
      
    -0.58
    .
    -0.58
    ↵↵
    -0.53
    <eos>
    -0.50
     C
    -0.50
     To
    -0.46
     On
    -0.46
     a
    -0.45
     again
    -0.45
    POSITIVE LOGITS
     Efq
    1.20
     myſelf
    1.04
    ſelf
    1.02
    )";
    1.02
     ―――――
    1.01
     $_"
    0.99
     AssemblyCompany
    0.98
     Monfieur
    0.97
     BoxDecoration
    0.96
    ."</
    0.96
    Activations Density 2.183%

    No Known Activations