© 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. 6882
    Prev
    Next
    INDEX
    Explanations

    CSS styling code and style attribute definitions

    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
    })));
    -0.50
    ']")
    -0.50
    coccal
    -0.48
    ']").
    -0.46
    WriteLiteral
    -0.44
    kussion
    -0.44
    ReusableCell
    -0.44
    NOPQRST
    -0.44
    })->
    -0.43
    getreten
    -0.42
    POSITIVE LOGITS
    EndGlobalSection
    0.79
     auffi
    0.77
     poffe
    0.76
     purpoſe
    0.75
    Personendaten
    0.74
     fubject
    0.73
     themſelves
    0.68
     resultCode
    0.68
     ſtate
    0.68
     pleaſure
    0.68
    Activations Density 0.020%

    No Known Activations