© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15335
    Prev
    Next
    INDEX
    Explanations

    the presence of specialized polynomials used in advanced mathematical analysis and topology

    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
     postres
    -0.59
     heilig
    -0.57
    Hentet
    -0.56
     chrétienne
    -0.56
    MUX
    -0.55
     régulier
    -0.54
     Roskov
    -0.54
     habitudes
    -0.53
     naturelle
    -0.52
     imprimée
    -0.52
    POSITIVE LOGITS
    AndPassword
    0.67
    centiles
    0.62
     onResponse
    0.61
     U
    0.59
    heartedly
    0.58
     apartment
    0.57
     Waray
    0.57
    TINGS
    0.57
    ArrowToggle
    0.57
    InjectAttribute
    0.57
    Activations Density 0.026%

    No Known Activations