© 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. 3027
    Prev
    Next
    INDEX
    Explanations

    markers indicating places where code comments or placeholders are inserted

    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
    Personendaten
    -0.51
     Stä
    -0.51
    hrter
    -0.45
    ")));
    -0.44
    ';
    -0.43
    長の
    -0.43
    Och
    -0.42
     ctypes
    -0.42
    '];
    -0.41
     handelt
    -0.41
    POSITIVE LOGITS
     TODO
    3.59
    TODO
    2.98
     FIXME
    2.13
    todo
    2.05
     todo
    1.83
    Todo
    1.73
     Todo
    1.67
     ToDo
    1.37
    ToDo
    1.20
    todos
    1.17
    Activations Density 0.004%

    No Known Activations