© 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. 6-RES-MATRYOSHKA-DC
    7. 678
    Prev
    Next
    INDEX
    Explanations

    mentions of source code or files

    oai_token-act-pair · gemini-2.0-flash
    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
     Tif
    -0.79
     Akismet
    -0.71
    Chim
    -0.71
    beforeEach
    -0.70
    ConstraintMaker
    -0.69
    AlterField
    -0.66
    ButterKnife
    -0.66
    Datuak
    -0.66
    UIControlState
    -0.66
    nastics
    -0.65
    POSITIVE LOGITS
     source
    2.45
     SOURCE
    2.34
     sources
    2.31
     Source
    2.31
     Sources
    2.17
    Source
    2.16
    source
    2.14
    sources
    2.02
    Sources
    1.92
    SOURCE
    1.90
    Activations Density 0.406%

    No Known Activations