© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5279
    Prev
    Next
    INDEX
    Explanations

    technical identifiers, codes, and numerical data patterns

    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
    ]));
    -0.59
    })*/
    -0.59
    новение
    -0.56
     forn
    -0.53
     estimés
    -0.52
    /*
    -0.51
     himo
    -0.50
     Pike
    -0.49
     estekak
    -0.49
    ยะ
    -0.49
    POSITIVE LOGITS
     Italijanski
    0.63
    tvguidetime
    0.56
    rrggbb
    0.55
     alberga
    0.53
    ">—
    0.51
    новништво
    0.50
     popo
    0.50
     Geller
    0.50
    ViewFeatures
    0.49
    isSuccessful
    0.49
    Activations Density 1.140%

    No Known Activations