© 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. 3447
    Prev
    Next
    INDEX
    Explanations

    instances of specific placeholder or variable-like tokens, such as "ik" or related variants

    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
     CWE
    -0.82
    BagConstraints
    -0.77
    RefNanny
    -0.76
    LayoutConstraint
    -0.76
    UserScript
    -0.75
    Personendaten
    -0.74
     CSM
    -0.73
    getColumnIndex
    -0.73
    CSM
    -0.72
    awtextra
    -0.72
    POSITIVE LOGITS
    ark
    1.17
    ARK
    1.13
     Ik
    1.11
    ik
    1.09
     Ark
    1.09
    mik
    1.07
     Duk
    1.06
    eak
    1.05
     ARK
    1.05
    tk
    1.04
    Activations Density 0.415%

    No Known Activations