© 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. 384
    Prev
    Next
    INDEX
    Explanations

    math or code.

    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
    IsPostBack
    -0.75
     ProgressDialog
    -0.72
    PerformLayout
    -0.71
    enterOuterAlt
    -0.69
    MessageDigest
    -0.69
    mobileqq
    -0.69
    Mane
    -0.67
    listdir
    -0.66
     defaultdict
    -0.66
    modelBuilder
    -0.66
    POSITIVE LOGITS
    x
    1.47
    getX
    1.46
     X
    1.42
     getX
    1.42
     Xavier
    1.38
     x
    1.37
     Xanth
    1.34
    X
    1.33
    xas
    1.32
    xes
    1.28
    Activations Density 3.455%

    No Known Activations