© 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. 2-RES-MATRYOSHKA-DC
    7. 7241
    Prev
    Next
    INDEX
    Explanations

    references to specific mathematical theorems or lemma numbers

    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
     Lemma
    -0.60
    CPtr
    -0.56
     []:
    -0.52
    UnknownFieldSet
    -0.52
    </td>
    -0.52
     Parker
    -0.50
    ////////////////
    -0.50
    vábbi
    -0.48
     …
    -0.48
    halb
    -0.48
    POSITIVE LOGITS
    thm
    2.88
    THM
    0.93
    thmus
    0.90
    thma
    0.81
    Diweddarwch
    0.81
     nakalista
    0.74
    ֹת
    0.72
     kaarangay
    0.71
    hythm
    0.69
    ClInclude
    0.68
    Activations Density 0.003%

    No Known Activations