© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2770
    Prev
    Next
    INDEX
    Explanations

    comment markers in source code

    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
     */
    -1.53
     */
    -1.40
    */
    -1.26
     **/
    -1.22
    **/
    -1.21
    )*/
    -1.13
     */
    -1.12
    .*/
    -1.08
    */
    -1.07
    /**
    -1.06
    POSITIVE LOGITS
    /*
    0.96
    ^(@)
    0.63
    cijos
    0.54
    헌
    0.52
     Bosch
    0.51
    XHR
    0.51
    remadura
    0.51
     NP
    0.50
     بدان
    0.50
     Nier
    0.50
    Activations Density 0.009%

    No Known Activations