© 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. 6472
    Prev
    Next
    INDEX
    Explanations

    interior details related to evidence in an investigative or forensic context

    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
     organisational
    -0.62
    ysław
    -0.61
    /*-
    -0.60
     Provisional
    -0.60
    SourceChecksum
    -0.58
    accumulative
    -0.58
    corbic
    -0.57
    aneously
    -0.57
    aneous
    -0.57
    illance
    -0.56
    POSITIVE LOGITS
     interior
    3.27
     Interior
    3.03
    Interior
    3.02
    interior
    2.95
     INTERIOR
    2.86
     interiors
    2.55
    INTERIOR
    2.28
     Interiors
    1.97
     exterior
    1.84
     interiores
    1.84
    Activations Density 0.004%

    No Known Activations