© 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
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 3785
    Prev
    Next
    INDEX
    Explanations

    whether packed data structures contain mismatched values

    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
    tagHelperRunner
    -0.90
    featureID
    -0.73
    MethodManager
    -0.69
    riwal
    -0.68
     dAtA
    -0.66
    principalColumn
    -0.66
    fromCharCode
    -0.66
    ContentAlignment
    -0.65
    eqn
    -0.63
    phosa
    -0.63
    POSITIVE LOGITS
     !=
    2.69
    !=
    2.14
    ]!=
    1.79
    ()!=
    1.74
     !==
    1.70
    )!=
    1.63
    !='
    1.43
    !=-
    1.37
    !==
    1.27
    ]!='
    1.26
    Activations Density 0.019%

    No Known Activations