© 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. 1-RES-MATRYOSHKA-DC
    7. 343
    Prev
    Next
    INDEX
    Explanations

    situations where access to a file or document is possible

    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
    AccessorTable
    -0.81
    TypedDataSet
    -0.68
    dataTables
    -0.63
    apunov
    -0.61
    letic
    -0.56
    Sucesor
    -0.56
    UserScript
    -0.56
    reggio
    -0.55
     Bunting
    -0.54
    fjspx
    -0.54
    POSITIVE LOGITS
     open
    4.38
    open
    3.98
     Open
    3.92
    Open
    3.86
     OPEN
    3.80
     opened
    3.72
    OPEN
    3.61
     opening
    3.47
     opens
    3.47
    opened
    3.22
    Activations Density 0.774%

    No Known Activations