© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13819
    Prev
    Next
    INDEX
    Explanations

    instructions or directives

    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
    tile
    -0.55
    новниш
    -0.50
    tiles
    -0.48
    쁨
    -0.47
    -------
    
    -0.47
     '';
    
    -0.46
     Kall
    -0.46
     "");
    
    -0.46
     &&
    
    -0.45
    ]]>
    -0.45
    POSITIVE LOGITS
     til
    2.63
     Til
    1.84
    Til
    1.75
     TIL
    1.30
     tilt
    1.02
     tilting
    1.02
     tilted
    0.94
    TagMode
    0.81
    +#+#
    0.81
    TIL
    0.79
    Activations Density 0.001%

    No Known Activations