© 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. 0-RES-MATRYOSHKA-DC
    7. 11372
    Prev
    Next
    INDEX
    Explanations

    sequences of approximate tilde symbols indicating varying degrees of similarity or amplitude

    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
     EconPapers
    -0.66
     Crusoe
    -0.63
    denn
    -0.58
    __*/
    -0.57
     indestru
    -0.55
     gyhoeddwyd
    -0.55
    τευ
    -0.54
    ModelSerializer
    -0.54
     مشين
    -0.53
     jsPsych
    -0.52
    POSITIVE LOGITS
    thenReturn
    0.61
    zeiti
    0.56
    toHaveBeenCalled
    0.53
     kív
    0.52
     JSONArray
    0.52
    CompoundButton
    0.52
    cheibe
    0.51
    toBeTruthy
    0.51
    kfree
    0.50
     (;;
    0.50
    Activations Density 0.035%

    No Known Activations