© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118865
    Prev
    Next
    INDEX
    Explanations

    wrt mathematical derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     valamint
    -0.08
    のため
    -0.07
    のための
    -0.06
     तसेच
    -0.06
    ेने
    -0.06
     kics
    -0.06
    สัมพันธ์
    -0.06
    満足
    -0.06
    <unused35>
    -0.06
     commitments
    -0.06
    POSITIVE LOGITS
    겠습니다
    0.06
     edhe
    0.06
     גם
    0.06
     लाज
    0.06
     কথাও
    0.06
     cerr
    0.06
     irregularly
    0.06
    ꒦
    0.06
     servlet
    0.05
    toCharArray
    0.05
    Activations Density 0.001%

    No Known Activations