© 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. 6-RES-MATRYOSHKA-DC
    7. 38
    Prev
    Next
    INDEX
    Explanations

    words frequently used in online forum posts or social media, particularly common phrases and questions

    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
     tevens
    -0.88
     następnie
    -0.83
     quæ
    -0.81
     således
    -0.81
     auffi
    -0.81
     также
    -0.77
     successively
    -0.77
    ]),
    -0.77
     concurrently
    -0.75
     eorum
    -0.75
    POSITIVE LOGITS
     stuff
    1.09
     really
    1.08
     guys
    1.06
     things
    1.04
     thing
    1.03
     somebody
    0.99
     something
    0.94
     you
    0.92
     REALLY
    0.91
     weird
    0.91
    Activations Density 20.997%

    No Known Activations