© 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. 6345
    Prev
    Next
    INDEX
    Explanations

    representations of code syntax and structure 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
    UnusedPrivate
    -0.77
    SourceChecksum
    -0.76
    Lähteet
    -0.72
     AssemblyCulture
    -0.71
    __(/*!
    -0.67
    IsMutable
    -0.66
    tiously
    -0.66
    }")
    -0.65
     Infórmanos
    -0.65
    ])):
    -0.64
    POSITIVE LOGITS
     potest
    0.59
     vettor
    0.56
     Romains
    0.53
     scoper
    0.52
     marbre
    0.52
    ChildScrollView
    0.52
     marins
    0.52
     gouver
    0.50
     marinho
    0.50
    MethodManager
    0.49
    Activations Density 0.090%

    No Known Activations