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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130793
    Prev
    Next
    INDEX
    Explanations

    tumour-necrosis factor beta

    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
     ತುಂಬಾ
    -0.06
     كتبت
    -0.06
    deltaTime
    -0.06
     ----------
    -0.06
     الرس
    -0.06
    BTW
    -0.06
     Ahora
    -0.06
    chette
    -0.06
     BTW
    -0.06
    ipramine
    -0.06
    POSITIVE LOGITS
     सु
    0.06
    如果
    0.06
    太郎
    0.06
    新
    0.06
    事情
    0.06
    一条
    0.05
    anol
    0.05
     nikdy
    0.05
    टोन
    0.05
    super
    0.05
    Activations Density 0.025%

    No Known Activations