© 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. 1-RES-MATRYOSHKA-DC
    7. 41
    Prev
    Next
    INDEX
    Explanations

    evaluations of intervention effectiveness and comparisons of different approaches

    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
    -
    -0.67
    k
    -0.66
     talking
    -0.62
     scared
    -0.61
     blew
    -0.61
     kidnapped
    -0.61
    /
    -0.61
     murdered
    -0.59
    คนที่
    -0.59
     tell
    -0.59
    POSITIVE LOGITS
     thereof
    1.13
    etheless
    1.03
     sufficient
    1.01
     notably
    1.01
     Notably
    1.01
     ſind
    1.00
     therein
    0.99
     saites
    0.99
     therefrom
    0.98
     Accordingly
    0.98
    Activations Density 17.431%

    No Known Activations