© 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. 832
    Prev
    Next
    INDEX
    Explanations

    references to complex natural phenomena or scientific concepts

    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
     beginnetje
    -0.62
     calciatore
    -0.60
    binder
    -0.59
    aarrggbb
    -0.58
     '{@
    -0.54
    wicket
    -0.53
    InteropServices
    -0.53
    thâu
    -0.51
    thio
    -0.50
     '\\;'
    -0.49
    POSITIVE LOGITS
     adult
    4.53
    Adult
    4.25
     Adult
    4.22
    adult
    4.16
     adults
    3.98
     ADULT
    3.92
     Adults
    3.80
    Adults
    3.67
    adults
    3.56
     adulte
    3.36
    Activations Density 0.127%

    No Known Activations