© 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. 3379
    Prev
    Next
    INDEX
    Explanations

    references to experimental data or measurements

    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
     information
    -0.70
     beginnetje
    -0.69
     Information
    -0.69
     Informações
    -0.66
     informations
    -0.65
    exitRule
    -0.65
    Information
    -0.65
     információk
    -0.64
    <?>>
    -0.63
    信息的
    -0.63
    POSITIVE LOGITS
    IBarButtonItem
    0.55
     Heute
    0.50
     maxLength
    0.48
    syntax
    0.47
    RUnlock
    0.46
    kuuta
    0.46
    Heute
    0.46
     ég
    0.45
    immobili
    0.45
    LError
    0.45
    Activations Density 0.024%

    No Known Activations