© 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. 935
    Prev
    Next
    INDEX
    Explanations

    references to user comments or feedback

    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
    rxjs
    -0.66
    fortawesome
    -0.62
    Informasi
    -0.60
    Recipes
    -0.50
     comp
    -0.49
     {},
    -0.49
    ={()
    -0.48
    toPromise
    -0.48
     Recipes
    -0.48
     rivol
    -0.47
    POSITIVE LOGITS
     comments
    4.19
     comment
    4.19
     Comment
    3.73
     Comments
    3.72
    comments
    3.63
    comment
    3.61
    Comments
    3.56
    Comment
    3.55
     commenting
    3.47
     COMMENT
    3.34
    Activations Density 0.116%

    No Known Activations