© 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. 0-RES-MATRYOSHKA-DC
    7. 12105
    Prev
    Next
    INDEX
    Explanations

    references to native code or native elements

    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
    DockStyle
    -0.61
    BorderFactory
    -0.59
     preferring
    -0.57
    iostream
    -0.57
    quelize
    -0.57
    arthed
    -0.55
    Vul
    -0.55
    LEncoder
    -0.54
    SizeF
    -0.54
     Ahu
    -0.53
    POSITIVE LOGITS
    native
    1.41
    pairs
    0.85
    consider
    0.75
     externi
    0.65
    ryl
    0.59
    tvguidetime
    0.59
     ModelExpression
    0.58
    MENAFN
    0.57
     nakalista
    0.56
    multer
    0.55
    Activations Density 0.004%

    No Known Activations